When we comprehend language, we create a mental representation of the situation that is described by the text [1], [2], [3]. Embodied theories of language propose that the information in such situation models is not merely abstract or symbolic, but rather is grounded in our bodily experiences [4], [5], [6]. This proposal implies that the representations we create or retrieve during language processing are similar to the representations we created when we actually experienced the respective situation. As a result, these conceptual representations include perceptual, lexical, semantic, and functional features and are shaped by people's world knowledge and beliefs [7]. There is ample evidence that people retrieve perceptual [8]–[10] and motoric [11], [12] information from memory while processing language. For example, they represent the visual features of a described object or action (such as shape, orientation, color, size, or direction of motion) while reading about a situation [13]–[21].

We ask whether language can affect the activation of a concept to such an extent that it improves or reduces the quality of a visual representation. Only a few studies that we know of have explored the quality of visual mental representations by manipulating the resolution [22], realism [23], vividness [24] or spatial frequency [15] of visual stimuli. In the current study we refer to a representation's quality in terms of perceptual vividness. We isolate the perceptual component of a representation in our definition of vividness, however, perceptual information is not exhaustive of a conceptual representation [10]. We make the critical assumption that when the perceptual component of a representation is activated to a greater extent, the availability of visual information -such as outline or color- will increase and thereby also what we call the vividness of a mental representation in memory. We assessed whether (a) the general activation of a concept, or (b) merely the activation of a concept's visual component affects vividness of a mental representation.

Many types of linguistic information can have an impact on the availability of concept information in memory. For example, objects that are present [25], visible [9], or spatially close [26] to a protagonist in a described situation are more accessible than objects that are absent, occluded, or farther away, respectively. For example, in one study participants read short stories describing a characters' view of an object that was either blocked (e.g., by a curtain) or not [9]. They were slower to respond to verification questions about objects that were occluded from view than to visible objects, suggesting that the accessibility of objects is reduced during recall when these objects are absent from the protagonist's view in a described situation. Another factor that affects the accessibility of an object is whether that object is goal-relevant. Information that is relevant to the protagonist's goal is retrieved faster than irrelevant information [27]–[32]. Responses to probe words are faster after reading texts in which a goal was achieved, compared to control texts that describe a simple completed action [27], [28]. This suggests that goal category information is more accessible than information that is irrelevant (neutral) to the goal.

To investigate whether and how concept availability affects the perceptual vividness of the associated conceptual representation in memory, we created short stories in which we manipulated both object presence (versus absence) and goal-relevance (versus irrelevance). In these described situations, object presence alters the visual components of a conceptual representation, whereas goal-relevance may alter the conceptual representation in a non-perceptual way. We formulated two main hypotheses.

The first major hypothesis is that increased availability of a concept in memory leads to increased perceptual vividness of the accompanying representation. Thus, both object presence and goal-relevance should exert an effect on recalled vividness (hypothesis 1). The most straightforward evidence would come from a pattern in which both object presence and goal-relevance increase perceptual vividness of the concept in memory. However, it is also possible that object presence and goal-relevance interact in specific ways. Out of the space of possible hypotheses in support of a mapping between concept availability and vividness, the following two seem particularly relevant.

Research on goal-relevance has shown a greater availability for objects that are relevant to the protagonist's goals rather than irrelevant [27]–[32]. As a result, presence or absence of an object may only be sufficiently salient for relevant objects. In other words, information about an object's presence may differentiate the availability of relevant concepts but not of irrelevant concepts [28]. In this case, we would expect an interaction in which an increased vividness for present compared to absent objects would only be detected for relevant objects (hypothesis 1a).

However, there is a parallel between our manipulation of presence and manipulations of negation in the literature. There is evidence that negated concepts do not simply reduce accessibility of a concept, but are even replaced by alternative opposites later in processing [33]–[36]. These robust effects of negation may result in a floor level accessibility to absent concepts, regardless of their goal relevance. In this case, we would expect an interaction in which an increased vividness for relevant compared to irrelevant objects would only be detected for present objects (hypothesis 1b).

The major alternative hypothesis is that only object presence affects perceptual vividness. Describing that an object is or is not present involves the visual aspects of a situation, whereas describing that an object is or is not relevant to a protagonist's goals does not. After all, if objects are present they are visible regardless of whether they are relevant to a protagonist's goals. Thus, this hypothesis predicts a main effect of presence but no main effect of goal relevance and no interaction (hypothesis 2).

The results from Experiment 1 showed that participants selected the transparent picture more often when reading about an absent object than a present object. This suggests that the recalled vividness of the picture was reduced after reading about absence of the referent object in the described situation (relative to the object being present in the described situation). These findings demonstrate that vividness (quality) indeed is an aspect of perceptual representations, and that this aspect is affected by language. Furthermore, goal-relevance did not significantly affect participants' decisions. This finding supports our second main hypothesis that a change in availability of a concept in memory does not necessarily lead to an altered perceptual vividness of the accompanying representation. This suggests that the current paradigm isolates the perceptual quality of a concept rather than the overall concept availability in a more abstract way (the way a probe word might do). In order to (a) optimize the possibility of detecting an effect of goal-relevance by including it as a within-subjects factor, (b) assess whether participants were aware of the purpose of the experiment, and (c) replicate our findings, we performed a follow-up experiment.

The results of Experiment 2 demonstrate that transparency judgments were affected by presence of the target object in the referential situation, suggesting that object absence reduced the recalled vividness of an associated picture. Furthermore, the results again demonstrated that described goal-relevance did not affect transparency judgments. If the current transparency paradigm would provide a measure of concept availability per se, we would have expected goal-relevance to affect the results. Therefore, these findings suggest that our paradigm specifically taps into a perceptual aspect of conceptual representations.

A potential criticism to this conclusion could be that our manipulation of goal-relevance did not sufficiently distinguish between different levels of concept availability. If, for example, goal-relevance in our stories did not affect the availability of the stored concept, it would also not affect the perceived vividness of the concept. To ensure that our linguistic manipulations indeed resulted in distinct levels of concept availability (with a higher availability for present and relevant objects as opposed to absent and irrelevant objects), we performed a production experiment.

We examined the quality of mental representations that are activated during language processing. Previous studies on perceptual representations manipulated visual object features to explicitly match or mismatch described object features. We did not. We manipulated the perceptual quality of the response options to the referent object and provided no matching decision alternative (both response options had a different transparency level than the original picture; thus, all answers were in principle incorrect). This manipulation revealed an implicit tendency of participants to select a more transparent (less vivid) picture after reading about a corresponding absent object. This implies that the entities that are not present in a described situation have a decreased perceivability in the referent representation. Studies that used probe words to assess the accessibility of visually absent, occluded, or distant objects found similar results in terms of availability of a corresponding concept [9], [25], [26]. Our current results extend these findings by specifying that a specific visual aspect of the concept representation is altered, namely its vividness.

To our knowledge, four previous studies have assessed perceptual quality [15], [22]–[24], only one of which is directly relevant to our research question [22]. Here, participants read sentences that manipulated the perceivability of an object (e.g., about a skier seeing a moose through fogged versus clean goggles), which facilitated response times to subsequently presented pictures of the object with a matching quality (low versus high visual resolution). Note that our current manipulation was more subtle. Our sentences did not mention perceived visual quality, they were embedded in stories in a task that did not require picture-to-sentence matching, and the pictures we presented in the experimental trials were not explicitly congruent or incongruent with the sentence in which the object was mentioned. Therefore, these findings are less susceptible to potential task-based strategies that participants might adopt to successfully perform the task. Any processing strategy in which participants did relate pictures to stories would have only been useful to distinguish experimental from filler stories, because this was the salient (but non-critical) manipulation.

Another difference is that we studied whether linguistic manipulations can qualitatively alter an experiential trace that was laid down within the experiment. All participants encoded the same pictures with identical (50%) transparency, thereby guaranteeing a baseline visual representation that was identical across conditions. Any difference in recollection of the encoded pictures should therefore be due to a difference in activation of this baseline trace. In other words, this paradigm taps into re-activation of a specific perceptual trace, rather than into a perceptual trace that might have been created ad hoc during language processing. For example, people may not have experience with seeing a moose through foggy goggles per se [22], but their (different) prior experience with the meaning of the words “foggy” and “moose” can still enable them to infer the approximate meaning of the sentence and envision a hazy moose. Therefore, it may be possible that people created a specific instant of a moose (of high or low visual quality), rather than recruiting a visual representation of a hazy moose from memory. For this reason, the current approach provides straightforward evidence that the strengthening of an experiential trace resulted in a better quality of the representation.

Whether a described object was relevant to the protagonist's goal did not affect the recalled transparency of encoded pictures. To ensure that this was not due to the stimuli we created, we performed a control experiment (Experiment 3) that demonstrated increased accessibility to relevant compared to irrelevant concepts, which confirms that our stimuli differentiated goal-relevance. A significant interaction revealed that the effect of relevance only occurred for stories in which the object was present. We hypothesized this pattern of concept availability based on the negation literature (hypothesis 1b) [33]–[36]. Overall, this pattern suggests that the concept availability of absent objects was reduced to floor level, resulting in an effect of goal-relevance in the production task only for present objects.

Even though our control experiment and previous research [27]–[32] convincingly showed that goal-relevance improves the accessibility of concept information, Experiments 1 and 2 did not reveal any effect of goal-relevance. This suggests that the current paradigm actually tapped into visual properties rather than overall concept availability or mere lexical accessibility, which supports hypothesis 2. It furthermore demonstrates that specific linguistic descriptions affect the mental representations we store in memory by differential reactivation of a perceptual trace. Based on these data alone, we cannot distinguish whether reading about absent objects did not recruit the stored perceptual information, or whether it did but the activation of the perceptual trace decayed more quickly. However, evidence from the negation literature suggests that early processing of negation/absence does not yet affect concept availability, only later processing does [33]–[36]. This suggests that the experiential trace of the referent concept might have been activated, but that it decayed (or was suppressed) shortly after. However, further research is needed to draw such conclusions within this framework.

People speak in terms of memories fading away, having a clear recollection of something, erasing images from one's mind, or having a situation fresh in memory. Our findings suggest that there is an actual physical component of mental representations that underlies these metaphors. In this study, we were able to isolate a qualitative visual component of concepts. This manifested itself in the recalled vividness of a stored representation. Even though objects were always explicitly mentioned in the text, the vividness of their corresponding representation in memory differed as a function of their described presence. These findings are in line with a grounded perspective on language processing, because they suggest that reading situation descriptions differentially re-activates experiential traces that were laid down previously.

The current approach provides new possibilities for future research. Given the wealth of demonstrations of perceptual involvement during language processing, we argue that at this point in time it is necessary to specify which aspects of concepts contribute to which aspects of language comprehension. This way, we will be able to formulate the strengths and weaknesses of the grounded (experiential) view on language processing and take new steps in understanding how people comprehend language and represent the external world.