Theory of Mind, how we understand others mental states, have been well studied in psychology. Recently it has been used for human robot collaboration because understanding others intentions and beliefs is a key capability for robots in order to interact with humans. However, inferring and reasoning about mental states during a Human-Robot interaction remains difficult. We present here how we apply Theory of Mind by implementing an implicit false belief task with UNDERWORLDS. In this task we explicitly maintain alternative world states associated to the beliefs of the humans and we show the interest of this approach.