We report three repetitions of Falk and Kosfeld's (2006) low and medium control treatments with 364 subjects. Each repetition employs a sample drawn from a standard subject pool of students and demographics vary across samples. Our results largely conflict with those of the original study. We mainly observe hidden costs of control of low magnitude that lead to low-trust principal-agent relationships. Our subjects were asked, at the end of the experimental session, to complete a questionnaire in which they had to state their work motivation in hypothetical scenarios. Our questionnaires are identical to the ones administered in Falk and Kosfeld's (2006) questionnaire study. In contrast to the game play data, our questionnaire data are similar to those of the original questionnaire study. In an attempt to solve this puzzle, we report an extension with 228 subjects where performance-contingent earnings are absent i.e. both principals and agents are paid according to a flat participation fee. We observe that hidden costs outweigh benefits of control which shows that control aversion is more prevalent under hypothetical than under real incentives. Still, in the low control treatment, we observe much weaker negative responses to control in our extension than in the original study. This observation, the fact that the original study uses real incentives, and preliminary findings on the relationship between demographics and the degree of control aversion lead us to conclude that Falk and Kosfeld's (2006) experimental regularities originate from the characteristics of their subjects.