In the well-known "dress" photograph, people either see the dress as blue with black stripes or as white with golden stripes. We suggest that the perception of colors is guided by the scene interpretation and the inferred positions of light sources. We tested this hypothesis in two online studies using color matching to estimate the colors observers see, while controlling for individual differences in gray point bias and color discrimination. Study 1 demonstrates that the interpretation of the dress corresponds to differences in perceived colors. Moreover, people who perceive the dress as blue-and-black are two times more likely to consider the light source as frontal, than those who see the white-and-gold dress. The inferred light sources, in turn, depend on the circadian changes in ambient light. The interpretation of the scene background as a wall or a mirror is consistent with the perceived colors as well. Study 2 shows that matching provides reliable results on differing devices and replicates the findings on scene interpretation and light sources. Additionally, we show that participants' environmental lighting conditions are an important cue for perceiving the dress colors. The exact mechanisms of how environmental lighting and circadian changes influence the perceived colors of the dress deserve further investigation.

People hiss and swear when they make errors, frown and swear again when they encounter conflicting information. Such error- and conflict-related signs of negative affect are found even when there is no time pressure or external reward and the task itself is very simple. Previous studies, however, provide inconsistent evidence regarding the affective consequences of resolved conflicts, that is, conflicts that resulted in correct responses. We tested whether response accuracy in the Eriksen flanker task will moderate the effect of trial incongruence using affective priming to measure positive and negative affect. We found that responses to incongruent trials elicit positive affect irrespective of their accuracy. Errors, in turn, result in negative affect irrespective of trial congruence. The effects of conflicts and errors do not interact and affect different dimensions of affective priming. Conflicts change the speed of evaluative categorisation while errors are reflected in categorisation accuracy. We discuss the findings in light of the "reward value and prediction" model and the "affect as a feedback for predictions" framework and consider the possible mechanisms behind the divergent effects.

No abstract