We present a framework for active agents, that integrates both the goal achievement desire of traditional A.I. and the survival instinct of new A.I. This framework is based on "motivations" as (1) a control mechanism for internal and external goal selection and (2) a generative mechanism for internal goal generation (usually resulting in one-action plans). We present an architecture and an implementation of the framework, that enables the agent designer to preset the motivational profile of the agent, or the agent itself to change its own motivational profile on the fly, given a priori or perceived knowledge of the environment characteristics. Empirical results involving a mobile robot in various office environments are presented.