Safety alignment is often conceptualized as a monolithic process wherein harmfulness detection automatically triggers refusal. However, the persistence of jailbreak attacks suggests a fundamental mechanistic decoupling. We propose the \textbf{ \underline{ D}}isentangled \textbf{ \underline{ S}}afety \textbf{ \underline{ H}}ypothesis \textbf{ (DSH)}, positing that safety computation operates on two distinct subspaces: a \textit{ Recognition Axis} ($\mathbf{ v}_H$, ``Knowing'') and an \textit{ Execution Axis} ($\mathbf{ v}_R$, ``Acting''). Our geometric analysis reveals a universal ``Reflex-to-Dissociation'' evolution, where these signals transition from antagonistic entanglement in early layers to structural independence in deep layers. To validate this, we introduce \textit{ Double-Difference Extraction} and \textit{ Adaptive Causal Steering}. Using our curated \textsc{ AmbiguityBench}, we demonstrate a causal double dissociation, effectively creating a state of ``Knowing without Acting.'' Crucially, we leverage this disentanglement to propose the \textbf{ Refusal Erasure Attack (REA)}, which achieves State-of-the-Art attack success rates by surgically lobotomizing the refusal mechanism. Furthermore, we uncover a critical architectural divergence, contrasting the \textit{ Explicit Semantic Control} of Llama3.1 with the \textit{ Latent Distributed Control} of Qwen2.5. The code and dataset are available at https://anonymous.4open.science/r/DSH.
Categories: cs.CR cs.AI cs.LG