This study examines the role of temperature as a driver of seasonal economic cycles. The study first presents a novel dataset of seasonal temperature and seasonal GDP. Stylised facts show that seasonal economic cycles are much more diverse than previous research suggested. The study then attributes seasonal economic cycles to temperature variability. For causal identification, the study proposes a novel econometric approach that accounts for expectations. The results suggest that seasonal temperature has a statistically significantly positive and economically large effect on seasonal GDP. Overall, a substantial share of seasonality in GDP timeseries appears to be due to weather. For a subsample of European countries, the effect of temperature can be attributed to sectors that are relatively more exposed to ambient environmental conditions. Projections of climate change suggest that seasonal economic cycles might substantially change in the future, with larger cycles expected for about half of the countries in the sample.