Objective: Depressive symptoms have been associated with Type 2 diabetes, but the temporal direction of this association and the underlying mechanisms remain unclear. The present study examined a potential bidirectional association between depressive symptoms and glucose levels in women and men, and the factors mediating this association. Method: The participants were from the Cardiovascular Risk in Young Finns Study, a prospective, population-based, cohort study (N = 2,534). Depressive symptoms were assessed using a modified Beck Depression Inventory. Fasting glucose was measured concurrently with depressive symptoms. To analyze the data, a multiple-group cross-lagged analysis and parallel multiple mediation in structural equation modeling were used. Results: Depressive symptoms in 2001 were positively associated with glucose levels in 2012 in women (β = .07, p = .023) but not in men (β = −.03, p = .45). This sex difference was statistically significant (p = .042). Glucose levels in 2001 did not predict depressive symptoms in 2012 in either women or men (ps = .96). Changes in body mass index, high-sensitivity C-reactive protein, alcohol consumption, or tobacco or cigarette smoking did not mediate the observed association (ps > .05). Conclusions: The results showed a positive association between depressive symptoms and glucose levels in women but not in men. The direction of this relationship seems to be from depressive symptoms to glucose levels rather than the reverse. Changes in body fat, inflammation, alcohol consumption, or tobacco or cigarette smoking may not play a mediating role in this observed association.