Abstract: In this paper we analyze walking sequences of an actor performing walk under eleven different states of mind. These walk sequences captured with an inertial motion capture system are used as training data to model walk in a reduced dimension space through principal component analysis (PCA). In that reduced PC space, the variability of walk cycles for each emotion and the length of each cycle are modeled using Gaussian distributions. Using this modeling, new sequences of walk can be synthesized for each expression, taking into account the variability of walk cycles over time in a continuous sequence.