To keep appointments and to honor social commitments, it is helpful to know what day it is. In practice, this requirement is not always met. The current studies were motivated by the informal observation that weekday confusions are common in daily life. For example, a person might think that it is Wednesday when in fact it is Thursday. In this paper we argue that confusions between weekdays are highly systematic, and that their distribution reveals much about mental representations of weekdays and their structure. As well as their theoretical interest, the findings have implications for decision making in a wide range of applied settings.

Errors in perception and behavior have often been used to infer underlying cognitive processes, and errors in time perception are no exception (see Gregory, 2009, for an interesting history) [1, 2]. On the millisecond scale, psychophysical studies have revealed distortions of subjective duration and event order associated with changes in physiological or attentional state [3–5]. At longer timescales, biopsychological studies have examined correlates of daily, monthly, and yearly cycles [6–12]. These natural time cycles are derived from the movements of celestial bodies—the rotation of the Earth on its axis, the orbit of the Moon around the Earth, and the orbit of the Earth around the Sun, respectively. Given the stability of these cycles on the evolutionary timescale, it may not be surprising that many biological processes track them [7]. However, much of modern human social activity is organized around the seven-day week [13, 14]. Unlike other calendar cycles, the seven-day week is an entirely human construct. This makes it an interesting cycle from a theoretical perspective. If weekday has psychological consequences, they must be driven by social factors such as cultural norms, rather than by physical or biological factors such as evolutionary pressure.

In fact, a small body of research has identified regularities between weekday and behavior, and also between weekday and mood. Across studies on these topics, two main patterns are emphasized. One is the so-called Blue Monday effect. In a wide range of situations and measures, outcomes are especially negative on Mondays. Many of these situations are non-trivial, as they pertain to health and economic matters. For example, heart attack risk is higher, suicide rate is higher, reported mood is lower, and stock returns are lower [15–20]. Especially positive outcomes on Fridays have also been reported, but with less consistency [21, 22]. This pattern suggests that, at least in terms of mood, Mondays (and possibly Fridays) may be qualitatively different from the other days of the week, which are themselves relatively undifferentiated.

A second pattern emphasizes gradual change from negative to positive through the week [23, 24]. For example, Ellis & Jenkins (2012) found that medical appointments on Mondays were much more likely to be missed than appointments on Fridays. Critically, the rate of missed appointments declined monotonically over the intervening days. This pattern suggests that, rather than being qualitatively different, Monday and Friday may be two extremes along a continuum of change.

The observation of weekday effects across domains as disparate as healthcare and economics hints at a potentially deep connection between the weekly cycle, core cognition, and downstream behavioral outcomes. Such a connection could have far-reaching implications, for the simple reason that so many of us are in phase with respect to the weekly cycle—when it’s Monday, it’s Monday for all of us. With such widespread synchrony, any psychological consequences of weekday should be highly correlated across individuals, and should tend to sum rather than to cancel out. The implication is that even small effects could scale up to systematic biases at the population level [24]. For example, it is already well established that affective state can influence decision-making [25]. If different days of the week are associated with different affective profiles, the outcome of a decision could depend on the day on which it is taken.

Our aim in this paper is to illuminate possible links between the weekly cycle and basic cognition by characterizing mental representations of weekdays. An important limitation of previous studies is that they have typically looked at a single outcome measure in isolation, such as reported mood or attendance rate. That is, they have analyzed similarity of weekdays along a single psychological dimension rather than their overall similarity, as indexed by confusability. Confusability is a particularly useful measure, as it requires no assumptions about which dimensions of similarity are most important [26–29]. However, the only previous studies to look at confusability of weekdays have done so from the perspective of serial order memory [30, 31]. On the face of it, serial order memory effects seem an unlikely explanation for weekly fluctuations in measures such as suicide and heart attack rates. For this reason, we take a very different approach that emphasizes the semantic and affective character of weekdays, rather than their order. The eventual aim is to understand behavioral effects of weekday for which serial order memory is not an easy explanation.

We began by tracking the prevalence of weekday confusability over the seven-day cycle (Study 1). To trace the resulting pattern to mental representations of weekdays, we then compared retrieval speed for the current day on different days of the week (Study 2). Finally, to identify determinants of weekday confusability at the level of mental representation, we analyzed semantic associations for each weekday, specifically their numerosity and affective valence (Study 3). Together, these studies show that confusability of weekdays is highly systematic, and imply that temporal cycles can shape cognition even when they are socially constructed.

In setting out this study, it is useful to distinguish between actual day (i.e., the current weekday according to the calendar) and apparent day (i.e., the weekday that the current day feels like, according to the respondent). This distinction allows us to test for mismatches between actual day and apparent day.

Our general approach to data collection was to elicit apparent weekday from respondents on each day of the week, so that data was collected over the whole seven-day cycle. In this way, we sought to establish whether mismatches are distributed evenly across the week, or whether they cluster in reliable patterns. Given that the working week (Monday to Friday) and the weekend (Saturday and Sunday) often involve rather contrasting routines, we expected that weekends might provide an especially salient marker in the weekly cycle. If so, then Mondays and Fridays should be relatively distinctive, because they begin and end the working week. In contrast, Tuesdays, Wednesdays, and Thursdays should be less distinctive, as none of them adjoins the weekend.

Our main interest was in the following patterns. First, the probability that the apparent day matches the actual day may differ through the week. For example, Fridays might consistently feel like Fridays, whereas Wednesdays might frequently feel like other weekdays. Although previous research has examined weekday confusion in the context of memory for past events [30, 31], none has addressed the more basic question of situating oneself in the seven-day cycle. Second, apparent day might be attracted more strongly by some days of the week than others. For example, apparent day might lag or lead actual day by a regular interval (e.g. one day). Alternatively, any day might be equally likely to be mistaken for any other. Third, mismatch rate may be determined in part by transitions between the weekend and the working week. To isolate the role of such transitions in regulating mental representations of weekday, we compared distributions of mismatches for a Normal week and a Bank Holiday week, in which the Monday was a public holiday.

To test whether midweek days are less salient than other days, we compared ease of access for different weekdays in a reaction time task. Based on the pattern of mismatches seen in Study 1, we predicted that it would be relatively hard to retrieve the current day on Tuesdays, Wednesdays, and Thursdays (resulting in slower response latencies), and relatively easy to retrieve the current day on Mondays and Fridays (resulting in faster response latencies). That is, differentiating between less distinct mental representations should take longer.

The main aim of this study was to characterize mental representations of weekdays by analyzing their semantic associations. Participants were asked to list associations for each weekday name in the context of a free association task. We first analyzed the number of associations for each day—a measure of representational richness or degree of elaboration [36]. To establish the generality of our lab-based findings, we conducted a complementary informatics analysis based on millions of webpages and books. We also analyzed the affective profile of participants’ weekday associations, using Affective Norms for English Words (ANEW) [37]. Given that midweek days seem to be especially confusable, we predicted that Tuesday, Wednesday, and Thursday would elicit relatively few associations compared with other weekdays. We also anticipated contrasting affective valence for Monday associations (negative) and Friday associations (positive) [21, 38].

We initially set out to investigate a widely experienced cognitive slip in which one day of the week feels like another. We found that mismatches between apparent day and actual day are highly systematic, and can be traced to the similarity of their mental representations. Converging evidence from large online survey data, experimental data, and informatics supports these conclusions. In Study 1, respondents reported mismatches between apparent day and actual day surprisingly often (37.5% of responses in a normal week). Mismatches were more frequent on midweek days than on other days, and mainly involved confusions with the immediately preceding or the immediately following day. A Bank Holiday Monday increased the overall number of mismatches (52.5% of responses), and skewed apparent day heavily towards the preceding day, so that Monday felt like Sunday, Tuesday felt like Monday, and so on. In a speeded production task (Study 2), we found that reaction times to retrieve the current day were fastest on Monday and Friday, slowest on Wednesday, and intermediate for Tuesday and Thursday. Finally, in Study 3, participants generated significantly fewer associations for midweek days (Tuesday, Wednesday, Thursday) than for other weekdays. This midweek dip was not explained by busyness—the number of scheduled events associated with each day. Google Search (website content) and Google Ngram Search (book content) each returned fewer hits for midweek days than for other days of the week, consistent with data from the associations task and data from the British National Corpus[40]. Analysis of the affective profile of these weekday associations (Pleasure, Arousal, and Dominance) revealed that the strongest contrast on each of these dimensions was between Monday and Friday. The loadings on each dimension varied gradually through the week, such that adjacent days were affectively more similar than non-adjacent days. We take from these findings that Monday and Friday are two extremes along a continuum, rather than being qualitatively different from other weekdays.

All of these findings can be understood in terms of mental representations of weekdays, their distinctiveness, and their richness, where distinctiveness is determined by the constellation of concepts associated with a given day, and richness is determined by the number of associations [42, 43]. On this view, mental representations of Monday and Friday are both rich and distinctive—Monday being rich and affectively negative, and Friday being rich and affectively positive. In contrast, mental representations of midweek days are more sparse and more homogenous—not only do they attract fewer associations, but those associations tend to be affectively neutral. Study 2 corroborates this view, by showing that the current day is more readily accessed on Mondays and Fridays than midweek. Together, these findings explain the pattern of weekday confusions seen in Study 1. First, the days on which mismatches between apparent day and actual day were most frequent (Tuesday, Wednesday, Thursday) are precisely those with sparse networks of associations. Second, the days that most strongly attracted mismatches (i.e. directly adjacent days) are precisely those with the most similar affective profiles.

We noted in Study 1 the quadratic function for weekday salience over the week, and a similar pattern emerged in Studies 2 & 3. This pattern resembles the serial position curves seen in sequence order memory studies, in which items at the beginning and the end of a sequence are better remembered than items in the middle. This resemblance raises the question of whether weekday effects are in any way specific to the weekly cycle, or whether they are merely another instance of a more general phenomenon, albeit one with potentially broad implications for everyday life. A full account of weekday effects would have to accommodate not only affective patterns of the type seen here (Study 3), but also the broad spectrum of weekday effects seen in health and economic settings—including effects on suicide rate, heart attack rate, mood, economic decision making, and other behaviors [15–24]. Whether or not all of these effects can be subsumed under a sequence memory account remains to be seen. An informative test would be whether the affective pattern observed here for weekdays holds for ordered items generally. If this affective pattern is driven solely by serial position, then associations with early items in any sequence should be low in pleasure, low in arousal, and high in dominance, whereas associations with late items should be high in pleasure, high in arousal, and low in dominance. Our own view is that there is more to the days of the week than their order, and that the interplay between weekday and cognition extends beyond sequence memory. The acid test will be whether aspects of cognition that are normally considered distinct from sequence memory (e.g. risk tolerance or face perception) vary systematically over the week. If so, the implications could be profound—not only for individual behavior [44–47], but also for psychological measurement.

Another promising line of research would be to investigate the underlying causes of psychological differentiation among weekdays. Our results already suggest an important role for the weekend in regulating psychological effects: First, the Bank Holiday effect in Study 1 implies that the weekend/working week transition is at least as important as absolute position in the seven-day cycle in determining apparent day [30, 31]. Second, the trajectories of the Pleasure, Arousal, and Dominance ratings in Study 3 reversed abruptly over the weekend, after following monotonic trends through the working week. It is not yet clear whether these effects of weekend are driven by changes in sleep patterns (e.g. reduction of sleep deficit), changes in activities (e.g. home versus work environment), or other factors. Studying populations for whom these factors are dissociated (e.g. shift workers or retirees) should help to disentangle these possibilities.

The present findings already advance our understanding of weekday processing in applied settings. We previously found [24] that weekday affects attendance rate for medical appointments. Confusion over the current day seems unlikely to explain this pattern. A confusability account should predict a midweek peak in missed appointments, as midweek days are the most confusable. The observed pattern of missed appointments follows the pattern of emotional responses to weekday cues seen in Study 3. Specifically, attendance was lower on days that elicit emotionally negative associations (e.g. Monday), and higher on days that elicit emotionally positive associations (e.g. Friday). This pattern suggests that medical appointments might be psychologically harder to face on some days of the week than on others. One way to test this possibility would be to compare weekday effects for more aversive and less aversive appointments. If the weekday effect is mediated by psychological resilience, then it may be stronger when an aversive procedure looms [48, 49].

For now, we show that effects of weekday on cognition can be traced to differences between mental representations of weekdays. Our studies also establish several facts relating weekday and cognition. First, mismatches between apparent day and actual day seem to be surprisingly common. Second, the distribution of mismatches across the week is highly systematic, with higher prevalence on midweek days than on other days. Third, mismatches are mainly intrusions from neighboring days, rather than more distant days. Fourth, a holiday Monday induces a one-day lag between apparent day and actual day. Fifth, the current day is easier to retrieve on Monday and Friday than midweek. Sixth, midweek days elicit fewer semantic associations than other weekdays. Seventh, midweek days occur less frequently than other days in webpages and books. Eighth, the emotional tone of weekday associations brightens from Monday to Friday.

We conclude that midweek days are confusable because their mental representations are sparse and similar. Mondays and Fridays are less confusable, because their mental representations are rich and distinctive. Previous studies have shown that natural temporal cycles (days, months, years) have psychological consequences. The present findings demonstrate that socially constructed temporal cycles can also shape our thinking.