Dunes and beaches are vulnerable to erosion during storm events. Numerical models can predict beach response to storms with fidelity, but their computational costs, the domain-specific knowledge necessary to use them, and the wide range of potential future storm and beach conditions can hinder their use in forecasting storm erosion for short- and long-term horizons. We develop an emulator, which is an efficient predictive model that behaves like a numerical model, to predict the morphologic response of the subaerial beach to storms. Specific emphasis is placed on providing antecedent beach states as an input to the emulator and predicting the post-storm profile shape. Training data include beach profiles at multiple stages in a nourishment life cycle to assess if such a framework can be applied in locations that nourish as a coastal defense policy. Development and application of the emulator is focused on Nags Head, North Carolina, which nourishes its beaches to mitigate hazards of storm waves, flooding, and erosion. A high-fidelity, process-based morphodynamic model is used to train the emulator with 1250 scenarios of sea-storms and beach profiles. The post-storm beach state is emulated with a parameterized power-law function fit to the eroded portion of the subaerial profile. When the emulator was tested for a sequence of real storms from 2019, the eroded beach profiles were predicted with a skill score of 0.66. This emulator is promising for future efforts to predict storm-induced beach erosion in hazard warnings or adaptation studies.