The rapid growth of energy consumption in commercial building operations hinders the pace of carbon emission reduction in China’s building sector, thus bringing great challenges to the successful realization of low-carbon development in China. This study uses historical data on carbon emissions from China’s commercial building operation to establish the STIRPAT model. The model parameters are estimated by LASSO regression, and the Grey Wolf Optimizer (GWO) is used to optimize the nonlinear coefficients of the LASSO regression model. The proposed model is used to evaluate historical carbon emission reduction levels and estimate the peak value of future carbon emissions in China. Findings show that: (1) The main driver forces of carbon dioxide emissions from the commercial building sector in China are population size, GDP per capita, and energy intensity of carbon emissions, and their elastic coefficients are 0.5097, 0.2870, and 0.2006, respectively. (2) The peak emissions of the commercial building sector are 1269.42 MtCO2, and the peak year is estimated to be 2029. Overall, this study analyzes the historical emission reduction levels and prospective peaks of carbon emissions in China’s commercial building sector from a new perspective. The research results can help governments and decision-makers formulate effective emission reduction policies and can also provide references for the low-carbon development of other countries and cities.