We prove a large deviation principle (LDP) and a fluctuation theorem for the entropy production rate (EPR) of the following d dimensional stochastic differential equation d𝑋𝑡=𝐴𝑋𝑡d𝑡+𝑄‾‾√d𝐵𝑡dXt=AXtdt+QdBt, where A is a real normal stable matrix, Q is positive definite, and the matrices A and Q commute. The rate function for the EPR takes the following explicit form: 𝐼(𝑥)=𝑥1+ℓ0(𝑥)√−12+12∑𝑑𝑘=1(𝛼2𝑘−𝛽2𝑘ℓ0(𝑥)‾‾‾‾‾‾‾‾‾‾‾‾‾√+𝛼𝑘)I(x)=x1+ℓ0(x)−12+12∑k=1dαk2−βk2ℓ0(x)+αk for x ≥ 0 and 𝐼(𝑥)=−𝑥1+ℓ0(𝑥)√+12+12∑𝑑𝑘=1(𝛼2𝑘−𝛽2𝑘ℓ0(𝑥)‾‾‾‾‾‾‾‾‾‾‾‾‾√+𝛼𝑘)I(x)=−x1+ℓ0(x)+12+12∑k=1dαk2−βk2ℓ0(x)+αk for x < 0, where α_k ±iβ_k are the eigenvalues of A and ℓ₀(x) is the unique solution of the equation ∣∣𝑥∣∣=1+ℓ‾‾‾‾‾√×∑𝑑𝑘=1𝛽2𝑘𝛼2𝑘−ℓ𝛽2𝑘√,−1≤ℓλ) = ∞ for 𝜆∉𝒟λ∉D, where 𝒟D is the domain of Λ. The functions Λ(λ) and I(x) satisfy the Cohen–Gallavotti symmetry properties: Λ(𝑥)=Λ(−(1+𝑥)),𝐼(𝑥)=𝐼(−𝑥)−𝑥,forall𝑥∈ℝΛ(x)=Λ(−(1+x)),I(x)=I(−x)−x, for all x∈R. In particular, the functions I and Λ do not depend on the diffusion matrix Q and are determined completely by the real and imaginary parts of the eigenvalues of A. Formally, the deterministic system with Q = 0 has zero EPR, and thus, the model exhibits a phase transition in that the EPR changes discontinuously at Q = 0.