The relation between affect and retrospective duration estimation has hardly been examined. In this paper, we contribute to filling this gap by studying the influence of arousal on the remembered duration of positive events. On the basis of the contextual change model, we expected that high‐arousal positive events would be remembered as longer compared with low‐arousal positive events. To test this hypothesis, we set up a naturalistic study in which participants were asked at the end of a pleasant amusement park ride at the local fair to rate how pleasant and aroused they felt during the ride as well as to estimate the ride's duration. Feeling more aroused during a ride was associated with longer estimates of the ride's duration. Results are discussed within the framework of retrospective time estimation models. Copyright © 2013 John Wiley & Sons, Ltd.