Geothermal thermosyphons (GTs) are increasingly used in many heating and cooling geothermal applications, owing to their high heat transfer performance. In this paper a combined response surface methodology and multi-objective desirability method is proposed for the investigation and optimization of the thermal performance of a geothermal thermosyphon. The filling ratio, temperature, and flow rate of the heat transfer fluid are selected as the designing parameters, and heat transfer rate and effectiveness are adopted as response parameters (objective functions). First, a dedicated experimental GT test bench filled with carbon dioxide (CO2) was built and subjected to different test conditions defined by RSM. A multi-level design of experiment-based response surface methodology (RSM) was used to establish corresponding models between the input parameters and responses. Various diagnostic tests were used to evaluate the quality and validity of the best-fit models, which explain respectively 98.9 and 99.2% of the output result's variability. Further, a surface response analysis of the effect of each input parameter on the responses was performed and a desirability function-based model was employed to determine the optimal combination of factors that would maximize the desired responses. The results revealed that the parameter-setting obtained using the proposed procedure satisfies the requirements of each response, with a desirability of 0.98.