This paper studies how and why consumers respond to unexpected, transitory income shocks. In a randomized control trial, I elicit marginal propensities to consume (MPC) out of different hypothetical income shock scenarios, varying the payment mode, the shock size, and the source of income. The results show respondents exhibit a higher MPC when exposed to a windfall paid out in cash or without any specification of the payment mode, respectively, compared to a windfall deposited in an instant-access savings account, suggesting consumers violate fungibility. Further, the MPC falls with the shock size, whereas it does not vary with the source of income. Using causal machine learning methods to explore treatment heterogeneity, I find that low liquidity, self-control problems, and a lack of cognitive sophistication contribute to MPC heterogeneity. The results are broadly in line with mental accounting theory.