Study #1 was approved by the Institutional Review Boards at Stony Brook University and New York University (approval number 6139). Study #2 was approved by the Institutional Review Boards at the University of California, Santa Barbara and Albert Einstein College of Medicine (approval number 2008–418). All participants provided written informed consent and received payment for their participation.

Procedures are described in detail in Acevedo et al., [22]. The stimuli were presented during a 12-minute session using a block design. Participants viewed two alternating face images interspersed with a count-back task for 20-seconds each, with 6 repetitions. The countback task consisted of counting backwards from a large number like 8011 on the screen, and was used to reduce carry-over effects as well as a control for arousal and attention, replicating procedures in Aron et al. [25].

Color photographs of facial stimuli, provided by participants prior to scanning, were digitized according to standard procedures and shown using Presentation software (Psychological Software Tools, Inc., Pittsburgh, PA). The Positive Partner (P) stimulus photo was of the long-term spouse or pre-marital/newlywed partner. To control for human face activations and familiarity, we used a photo of a Highly-Familiar Neutral (HFN) acquaintance matched for gender, age and length of time known to the participant. Participants were instructed to think about romantic experiences with the partner that were not sexual in nature to control for event memory, neutral experiences with the HFN acquaintance. After each set of images, while still in the scanner, participants rated the emotional intensity elicited by each stimulus. These data are presented in Acevedo et al. [22] Post scan interviews were conducted to assess whether instructions were followed. Participants were asked to describe their thoughts and feelings during the experiment, and whether they were able to do the count-back task. Also, all photos were rated for attractiveness and image quality by six independent raters and there were no differences between P and HFN faces. For details see Acevedo et al. [22]. These procedures have been used in four separate fMRI studies carried out by our group [22], [25]–[27], and by others [28]–[31]. They result in replicable activations associated with romantic love and attachment.

For Study #1 [22], data were analyzed using SPM2; for Study #2, data were analyzed using SPM5 (http://www.fil.ion.ucl.ac.uk/spm). For preprocessing, functional EPI volumes were realigned to the first volume, smoothed with a Gaussian kernel of 6 mm, and then normalized to the MNI T1 image template. No participant showed movement greater than 3 mm (whole voxel) motion. After preprocessing, analyses were carried out using a mixed effects general linear model, with participants as the random-effects factor and conditions as the fixed effect. The P-versus-HFN contrast was created.

For the Long-Term Love group, Study #1, scores on the Curious/Energetic scale of the FTI co-varied with activations in the region of the right substantia nigra (SN: r = .75, p = .001) and right dorsolateral prefrontal cortex (DLPFC, BA10: r = .74, p = .001) (Figure 1A–B, Table 1). These results were replicated in Study #2, the Newlywed group (SN: r = .50, p = .04; DLPFC: r = .71, p = .001; Figure 1C–D; Table 1). Also, a small area of the auditory cortex (BA22) and the SI gustatory area (BA43) were correlated with Curious/Energetic scores in both Study #1 (BA22: r = .79, p = .001; BA43: r = .82, p = .001) and Study#2 (BA22: r = .79, p = .001; BA43: r = .80, p = .001), but in different regions (Table 2).

Scores on the Cautious/Social Norm Compliant scale correlated with activation in the left ventrolateral prefrontal cortex (vlPFC) in Study #1 (r = .70; p = .002; Figure 1E–F) and in Study #2 (r = .50; p = .03; Figure 1G–H; Table 1).

Scores on the Analytical/Tough-minded scale co-varied with activation in the occipital (BA18) and parietal cortex (BA7) in Study #1 (BA18: r = .71, p = .001; BA7: r = .79, p = .001) and Study#2 (BA18: r = .59, p = .01; BA7: r = .63, p = .01). Scores also co-varied in both studies with activation in an area of the right DLPFC (BA10) in Study# 1(r = .74, p = .001) and Study# 2 (r = .71, p = .001), although regionally different from that associated with the Curious/Energetic scale; in a region of the right and left dorsomedial prefrontal cortex (DMPFC) in Study# 1(right: r = .70, p = .002; left: r = .78, p = .001) and Study#2 (right: r = .55, p = .02; left: r = .56, p = .02); and a region of the right orbitofrontal cortex (rOFC) in Study #1 (r = .78, p = .001) and Study#2 (r = .60, p = .01). See Table 1.

Scores on the Prosocial/Empathetic scale correlated with activation in the right inferior frontal gyrus (IFG) in Study#1 (r = .66, p = .005) and Study# 2 (r = 65; p = .003); the left anterior insula (AI) in Study#1 (r = .57, p = .02) and Study# 2 (r = .54, p = .02); and the left fusiform gyrus in Study# 1 (r = .62, p = .007) and Study#2 (r = .64, p = .004). See Table 1.

Both groups showed an adequate range of scores for each dimension, from 15 to 35 out of a possible range from 0–42 (Figure 1). Thus, the scores included answers from Disagree through Agree, to nearly Strongly Agree.

Overall, in these two groups of volunteer participants, 8 showed highest scores on the Curious/Energetic dimension, 11 showed highest scores on the Cautious/Social Norm Compliant dimension, 4 showed highest scores on the Analytical/Tough-Minded dimension and 12 showed highest scores on the Prosocial/Empathic dimension.

The brain’s physiological BOLD response (parameter estimates calculated by SPM) was not 0 or negative at the lowest scores for any of the temperament dimension correlations (Figure 1). All responses were positive, although some more than others, producing the positive correlation.

The SN is a major group of cells in the dopamine system [37]–[41] where dopaminergic influences can be expected. Scores on the Curious/Energetic scale of the FTI co-varied with activation in the exact same region of the SN in both Study #1 and Study #2. Although dopamine activity was not directly monitored in this study, the SN is rich with dopamine cells and receptors, and its activation can have widespread effects on behavior through dopamine’s actions [37]–[41]. The replication of activation in this region is strong evidence that the Curious/Energetic scale of the FTI measures activity involving the dopamine system more than the other scales. Although this temperament dimension certainly uses other transmitter systems for this task, the dopamine system may be a primary influence. It is important to note that this is a region different from the dopamine-rich ventral tegmental area that is activated in most participants in love regardless of personality [22], [25]–[27].

For the younger pre-marital and newlywed group, the norepinephrine-rich region of the locus coeruleus was also correlated with scores on the Curious/Energetic scale. This is additional support for the idea that the dopamine and norepinephrine systems are important physiological correlates of the Curious/Energetic temperament dimension. Extraversion, one of the Big Five traits that has been associated with high energy has also been associated with the dopamine system [12].

Scores on the Cautious/Social Norm Compliant scale co-varied with activation in regions of the left vlPFC in both Study#1 and Study #2. The two vlPFC regions in both studies were associated with “social norm compliance” behavior in a previous study [32], and social norm compliance is linked with activity in the serotonin system [20], [42]. Although there are many neurotransmitter and receptor types in the vlPFC, serotonin is one of them [43], [44]. These results are indirect evidence that the Cautious/Social Norm Complaint scale of the FTI could measure activity associated with the brain’s serotonin system.

In both studies, scores on the Analytical/Tough-minded scale correlated with activation in primary areas of the occipital cortex, which mediates basic visual functions. These results are consistent with the prediction that this temperament dimension is influenced by testosterone, as suggested by several studies. In one study, men were more sensitive than women in a visual contrast sensitivity task; men showed greater visual acuity for detail and rapidly moving stimuli [45]. Endogenous testosterone is associated with enhanced attention to visual details [46]. Also, in an fMRI study, light stimulation had a greater effect on the occipital cortex in men than in women [47], and men excel at seeing in the light [48]. Animal studies have shown that, during development, males have a larger number of androgen receptors in the occipital cortex than do females [49], and androgen receptors persist in these cortical regions in adult primates, including the visual cortex [50]. Equally relevant, using magnetic resonance imaging to measure tissue density, anatomical studies have found sex differences in the occipital cortex [51], [52]. Thus, the occipital cortex is an area where sex differences have been documented functionally and anatomically, and the positive correlation between the Analytic/Tough-minded temperament dimension and occipital cortex activation is evidence that the Analytical/Tough-minded scale may measure some aspect of testosterone system activity.

In addition, areas of the parietal cortex correlated with scores on the Analytical/Tough-minded scale in both studies. The parietal cortex is involved in spatial/mathematical thinking, and anatomical studies show sexual dimorphism in this region associated with male/female differences in spatial/mathematical tasks [51], [53]–[55]. The parietal regions identified in these other studies were within 10 mm of the regions where a correlation was found with the Analytical/Tough-minded dimension. General measurements of parietal lobe structure and function also show male/female differences [56]–[58]. Further, prenatal endogenous testosterone priming has been linked with enhanced visual-spatial perception and mathematical skills [59]–[61]. Activation of these parietal regions, as well as activation in the DLPFC, may reflect the “analytic” aspect of the proposed Analytical/Tough-minded temperament dimension [47], [49]–[58], [62], [63].

Regions of the DLPFC, DMPFC and OFC also correlated with the Analytical/Tough-minded scale. These are areas involved in cognition and reward assessment e.g. [64]–[73].

The DLPFC, DMPFC, OFC and each of the specific regions correlated with the Analytical/Tough-minded dimension are within 10 mm of an area that discriminated between men and women in anatomical measurement studies of regional gray matter size and density [51], [52], [62]. Thus, all regions correlated with the Analytical/Tough-minded temperament dimension have shown anatomical differences between men and women, strongly suggesting a hormonal influence [47], [49]–[58], [62].

Scores on the Prosocial/Empathetic scale correlated in both studies with activity in the IFG, AI and fusiform gyrus. These areas are associated with mirror neurons or empathy [33], [34]. Empathy is regularly associated with estrogen activity. Moreover, each of these regions is associated with sex differences, sometimes directly attributed to estrogen activity. Witte et al., 2010 [74] found salivary 17beta-estradiol to be associated with gray matter volume in the fusiform gyrus in a region close to the region correlated with scores on the Prosocial/Empathetic scale of the FTI (within 10 mm). They also found a correlation for 17beta-estradiol in the IFG on the other side of the brain, which correlated with the Prosocial/Empathetic scale of the FTI [74]. Cheng et al., 2009 [75] found greater gray matter volume in women compared to men in the pars opercularis, near the IFG region that correlated with Prosocial/Empathetic scores in the present study. Cheng et al, 2009 [76] also found a correlation between gray matter volume and empathy measures in men and women in the pars opercularis. Using a multimodal approach, Feis et al. [51] report differences between men and women in brain tissue (volume, density) in the AI and IFG cortex. Last, Yamasue et al., 2008 [76] found greater gray matter volume in the IFG in women; these women also showed greater cooperativeness than the men in the study. These data from several sources support the prediction that the Prosocial/Empathetic scale of the FTI is measuring influences of the estrogen system.

The replication of the results in two separate studies indicates that the effects are reliable. The results show an association with a dopamine-rich brain region, as well as testosterone and estrogen influences documented in many other studies. Thus, one out of the four dimensions was directly associated with the predicted biological system, and the two sex hormone-based dimensions were associated with sex hormone structural and functional effects in the brain. Moreover, the Cautious/Social Norm Compliant dimension was associated with predicted regions based on behavior, and serotonin could certainly be involved.

The replication of these results in different age groups also shows the robustness of the dimensions over the life course. The subjects in Study #1 ranged in age from 39 to 67 (M = 52.85) and were in marriages of considerable duration (M = 21.4 years). Subjects in Study #2 ranged in age from 21 to 32 (M = 27.5) and were in pre-marital or newlywed relationships of far shorter duration (M = 4.3 years). Other research shows that a range of personality variables are relatively stable over the life course [77]–[80], and we predict that the four dimensions reported here will be consistent within individuals, also.

A few correlations were found in only one of the two groups studied. Of special note, a correlation with activation in the locus coeruleus region, rich in norepinephrine-producing cells, was found for the Curious/Energetic scale of the Pre-marital/Newlywed group. This association is predicted by the FTI model. But it is not known why this correlation appeared in one group and not the other. A range of factors may be involved, including variations in mean age and composition of each group, variations in the degree of feelings of romance and attachment expressed by participants in each group, and/or a difference in scanner sensitivity.

Also regarding the Curious/Energetic scale, there was a correlation with the auditory cortex; but the two groups show this activity on different sides of the brain. The two groups also showed a correlation between the somatosensory/gustatory area and scores on the Curious/Energetic scale of the FTI, but these activations were farther away from each other than our criterion for replication would allow. Nevertheless, these correlations suggest that auditory and taste sensations may be especially important to those individuals expressive of traits associated with the Curious/Energetic dimension. Indeed, sensation-seeking individuals score high on scales that measure sensation-seeking through the mind and senses [81]; these individuals prefer arousing sensory stimuli in the arts [82], music [83], live entertainment [84] and food preferences [85]. Perhaps the subjects who were primarily expressive of the Curious/Energetic scale of the FTI had more arousing auditory and sensory/gustatory-related thoughts and memories about their partner while doing the task.

To explore the full complement of biological processes associated with the trait constellations measured by the FTI, several types of studies need to be designed and implemented. Although investigations of genetic markers related to the dopamine and serotonin systems are in progress, it may take decades before genome-wide association studies will be able to measure the full array of genes that contribute to any of these proposed trait constellations. Besides genetic studies, direct measurement of hormones in saliva is possible, and positron emission tomography could be used to confirm specific transmitter involvement in the four dimensions proposed here. However, there is an advantage to seeing the functional associations of fMRI before embarking on direct and sometimes invasive measurements of the transmitters and hormones directly. For hormone levels, especially, which vary widely throughout the day, it is better to have a functional measure of the effect the hormone has had, such as regional brain size and density variations and regional activation correlations, before undertaking direct level measurements.

Further, the current FTI and its scoring describes only four major trait constellations. Future investigations may uncover lower level trait constellations, as well as expose the highly complex relationships among these temperament dimensions and with other dimensions of temperament.

In addition, Study#1 and Study#2 investigated brain activity while participants did only one task. Additional brain scanning studies (fMRI) of different groups and different tasks must be conducted. Interestingly, the local brain response was never zero or negative for a region correlated with one of the dimensions (Figure 1). All participants showed some response in the region where a significant correlation was found, suggesting a general “social response” to a romantic partner in each region, but greater for some temperament dimensions than for others. This suggests that the findings are a “social response signature” for each dimension, as we sought to determine. There might be a different set of regions involved for each dimension if the task had been a mathematical one, for example. Importantly, the four FTI subscales produced unique high activations in separable brain regions; we predict that these temperament dimensions will be discriminable in different kinds of tasks.

Scores on the Curious/Energetic scale of the FTI co-varied with activation in a region of the substantia nigra in two independent studies, providing strong evidence that the Curious/Energetic scale could measure some aspect of the dopamine system activity in people thinking about their romantic partner. Scores on the Cautious/Social Norm Compliant scale co-varied in both studies with activation in the ventrolateral prefrontal cortex, in a region associated with “social norm compliance,” a trait linked in the biological literature with the serotonin system, indirect evidence that the Cautious/Social Norm Compliant scale measures some aspect of the serotonin system. Scores on the Analytical/Tough-minded scale co-varied in these two studies with activity in regions of the occipital, parietal, orbitofrontal and prefrontal cortex, regions affected by sex hormones and associated with sex differences in behavior. Last, scores on the Prosocial/Empathetic scale correlated in both studies with activity in regions associated with mirror neurons and concomitant empathy, a trait linked with the estrogen system, and brain regions structurally affected by gender. Although each of the temperament dimensions use many other neurochemical systems, one or two appear to predominate in each dimension under these specific task circumstances.

These findings support the hypothesis that the four broad temperament dimensions measured by the FTI are associated with separable brain systems. Because the results were replicated in two independent studies using participants of significantly different ages, these data also suggest that traits associated with these four temperament dimensions may be relatively stable across the life course. Finally, the results suggest that there could be a unique “neural signature” for each temperament dimension associated with close, love relationships.