This paper examines the stationarity of carbon dioxide (CO2) emissions per capita for a set of 36 countries covering the period 1870-2006. We employ recently developed unit root and stationarity tests that allow for the mean reverting process to be nonlinear and take into account cross sectional dependence. By grouping countries according to their geographical proximity, the importance of cross sectional dependence in panel unit root and stationarity tests is revealed. Using a recently developed nonlinear panel unit root test, we find strong evidence that the per capita carbon dioxide emissions over the last one hundred and fifty years are stationary. Our nonlinear specification captures the dynamics of the emissions time series data more effectively and we obtain evidence supporting stationarity for all country groups under study.