fMRI studies of higher level cognitive processing stretch current stimulus presentation paradigms. Adding the capability for subjects to intuitively interact with a virtual world has huge potential for advancing such studies. Gaze tracking can provide rich information about attention, but maintaining accurate gaze estimation is compromised by head movement and most systems do not allow visual interaction. We describe a gaze interaction interface that exploits each new fixation to achieve robust and accurate perfromance even during head movement. This opens opportunities for naturalistic, flexible and complex fMRI experiments, particularly for challenging populations like children and those with cognitive difficulties.