Managing and dealing with variability is a common challenge in the daily practice of many enterprises and organizations. Recent studies have observed that digital transformation and artificial intelligence solutions lead to changes in enterprises that simultaneously require variability on several levels of an enterprise (for example, business processes, data architecture, and services). Enterprise architecture models are considered a suitable way to visualize and manage dependencies between different levels of an enterprise. Still, there is not much work on managing variability in enterprise architectures. This paper aims to structure the existing research work and tribute to a better understanding of future investigation needs. We argue that there is a need for new constructs in enterprise architecture models that allow for expressing dependencies between variations on different enterprise architecture levels.