Our paper describes the creation and evaluation of a Distributional Semantics model of ancient Greek. We developed a vector space model where every word is represented by a vector which encodes information about its linguistic context(s). We validate different vector space models by testing their output against benchmarks obtained from scholarship from the ancient world, modern lexicography, and an NLP resource. Finally, to show how the model can be applied to a research task, we provide the example of a small-scale study of semantic variation in epic formulae, recurring units with limited linguistic flexibility.