This article presents a stochastic geometric framework to model and analyze spatially correlated blockage in a vehicular network. First, we model the vehicular obstacles as a Boolean model on a line using stochastic geometry. Then, we represent signal paths from transmitters to receivers as a graph from the transmitter point process to the receiver point process. The blockage of a signal path occurs if and only if any obstacle obstructs the corresponding edge. Since the signal blockage occurs by obstacles, the proposed determination of blockage preserves the spatial correlation of signal paths. Under the proposed framework, we derive the blockage probability of a typical vehicle. In addition, we derive the probability that a typical vehicle is in the line of sight (LOS) with respect to at least one transmitter. The proposed framework and blockage analysis will be instrumental to the analysis of LOS-critical applications such as positioning or mmWave communications in vehicular networks.