Dissecting a hot molecular core: the case of G31.41+0.31

Context. The role of disks in the formation of high-mass stars is still a matter of debate but the detection of circumstellar disks around O-type stars would have a profound impact on high-mass star formation theories. Aims. We made a detailed observational analysis of a well known hot molecular core lying in the high-mass star-forming region G31.41+0.31. This core is believed to contain deeply embedded massive stars and presents a velocity gradient that has been interpreted either as rotation or as expansion, depending on the authors. Our aim was to shed light on this question and possibly prepare the ground for higher resolution ALMA observations, which could directly detect circumstellar disks around the embedded massive stars. Methods. Observations at sub-arcsecond resolution were performed with the Submillimeter Array in methyl cyanide, a typical hot molecular core tracer, and (CO)-C-12 and (CO)-C-13, well known outflow tracers. We also obtained sensitive continuum maps at 1.3 mm. Results. Our findings confirm the existence of a sharp velocity gradient across the core, but cannot confirm the existence of a bipolar outflow perpendicular to it. The improved angular resolution and sampling of the uv plane allow us to attain higher quality channel maps of the CH3CN lines with respect to previous studies and thus significantly improve our knowledge of the structure and kinematics of the hot molecular core. Conclusions. While no conclusive argument can rule out any of the two interpretations (rotation or expansion) proposed to explain the velocity gradient observed in the core, in our opinion the observational evidence collected so far indicates the rotating toroid as the most likely scenario. The outflow hypothesis appears less plausible, because the dynamical time scale is too short compared to that needed to form species such as CH3CN, and the mass loss and momentum rates estimated from our measurements appear too high.