This paper describes a novel method for representing different facial expressions based on the shape space vector (SSV) of the statistical shape model (SSM) built from 3D facial data. The method relies only on the 3D shape, with texture information not being used in any part of the algorithm, that makes it inherently invariant to changes in the background, illumination, and to some extent viewing angle variations. To evaluate the proposed method, two comprehensive 3D facial data sets have been used for the testing. The experimental results show that the SSV not only controls the shape variations but also captures the expressive characteristic of the faces and can be used as a significant feature for facial expression recognition. Finally the paper suggests improvements of the SSV discriminatory characteristics by using 3D facial sequences rather than 3D stills.