Recent research has provided evidence for the role of norm-based coding in face recognition (e.g. Leopold et al., 2001). In such a model, any given face can be represented by a vector from the norm, with the difference between two faces being the difference between the two vectors. However, as has previously been suggested it is also possible to conceive of a model in which the angle between two vectors provides relevant information for differentiating faces. Two experiments investigated this possibility using a face matching paradigm. Discrimination was found to be better when two faces lay on different vectors than when they were the same physical distance apart but lying on the same vector. The results favour a specific type of norm-based model suggesting that vector angle is important in face perception.