The energy consumption of buildings has traditionally been driven by the consumption habits of building occupants. However, with the proliferation of smart building technologies and appliances, automated machine decisions are beginning to impart their influence on building energy behavior as well. This is giving rise to a disconnect between occupant energy behavior and the overall energy consumption of buildings. Consequently, researchers can no longer leverage building energy consumption as a proxy for understanding human energy behavior. This paper addresses this problem by exploiting the habitual and sequential nature of human energy consumption. By studying the chronology of human energy actions, the results of this work present a promising new approach for non-intrusively learning about human energy behavior directly from building energy demand data.