Masked prime stimuli can bias "free" choices between response alternatives

Stimuli presented below the threshold of awareness can systematically influence choice responses determined by the instructed stimulus-response (S-R) mapping (task set). In this study, we investigated whether such stimuli will also bias a free choice between two response alternatives under conditions in which this choice subjectively appears to be internally generated and free. Participants had to respond to targets preceded by masked arrow primes. Left-pointing and right-pointing arrow targets required left or right responses, whereas randomly interspersed "free-choice" targets indicated that the participants were free to choose either response. Although masked primes could not be consciously discriminated, they systematically affected not only performance to arrow targets, but also the free choice between response alternatives. This demonstrates that apparently "free" choices are not immune to nonconsciously triggered biases. However, in blocks in which no specific S-R mapping was imposed, masked primes did not affect free-choice performance, indicating that these effects are not automatic but are determined by currently active task sets.