Positive and negative moods have been shown to increase likelihood estimates of future events matching these states in valence (e.g., E. J. Johnson & A. Tversky, 1983). In the present article, 4 studies provide evidence that this congruency bias (a) is not limited to valence but functions in an emotion-specific manner, (b) derives from the informational value of emotions, and (c) is not the inevitable outcome of likelihood assessment under heightened emotion. Specifically, Study 1 demonstrates that sadness and anger, 2 distinct, negative emotions, differentially bias likelihood estimates of sad and angering events. Studies 2 and 3 replicate this finding in addition to supporting an emotion-as-information (cf. N. Schwarz & G. L. Clore, 1983), as opposed to a memory-based, mediating process for the bias. Finally, Study 4 shows that when the source of the emotion is salient, a reversal of the bias can occur given greater cognitive effort aimed at accuracy. Affective states have been shown to influence many types of decisions that individuals regularly confront (for reviews, see Forgas, 1995; Schwarz & Clore, 1996; Wegener & Petty, 1996). Among these is the assessment of the frequencies with which, or the likelihoods that, certain events will occur (Johnson & Tversky, 1983; Mayer, Gaschke, Braverrnan, & Evans, 1992). Sometimes, the consequences of such judgments can be relatively minor, such as when trying to determine if the Yankees will trounce the Red Sox or if an admired coworker will accept an invitation for a date. Other times, however, the consequences can be quite profound, such as when considering the chances of developing lung cancer from smoking, the odds of contracting AIDS from practicing