Most computational story generation systems lack the ability to generate new types of imaginary objects that play functional roles in stories, such as lightsabers in Star Wars. We present an algorithm that generates such imaginary objects, which we call gadgets, in order to extend the ontological expressivity of existing, planning-based story generation systems. The behavior of a gadget is represented as a plan including typical events that happen when the gadget is used. Our algorithm creates gadgets by extrapolating and merging one or more commonly known objects in order to achieve a narrative goal provided by an existing story generator. We extend partial-order planning to establish open conditions based on analogies between concepts related respectively to common objects and the gadget. We show the algorithm is capable of generating gadgets created by human.