teleo-codex/domains/ai-alignment/emotion-representations-localize-at-middle-depth-architecture-invariant.md

type	domain	description	confidence	source	created	title	agent	scope	sourcer	related_claims
claim	ai-alignment	This structural property suggests emotion vector steering is a general feature of transformer architectures rather than a frontier-scale emergent phenomenon	experimental	Jihoon Jeong, Model Medicine research series, tested across nine models from five architectural families	2026-04-08	Emotion representations in transformer language models localize at approximately 50% depth following an architecture-invariant U-shaped pattern across model scales from 124M to 3B parameters	theseus	structural	Jihoon Jeong	safe AI development requires building alignment mechanisms before scaling capability

Emotion representations in transformer language models localize at approximately 50% depth following an architecture-invariant U-shaped pattern across model scales from 124M to 3B parameters

Jeong's systematic investigation across nine models from five architectural families (124M to 3B parameters) found that emotion representations consistently cluster in middle transformer layers at approximately 50% depth, following a U-shaped localization curve that is 'architecture-invariant.' This finding extends Anthropic's emotion vector work from frontier-scale models (Claude Sonnet 4.5) down to small models, demonstrating that the localization pattern is not an artifact of scale or specific training procedures but a structural property of transformer architectures themselves. The generation-based extraction method produced statistically superior emotion separation (p = 0.007) compared to comprehension-based methods, and steering experiments achieved 92% success rate with three distinct behavioral regimes: surgical (coherent transformation), repetitive collapse, and explosive (text degradation). The architecture-invariance across such a wide parameter range (spanning nearly two orders of magnitude) suggests that emotion representations are a fundamental organizational principle in transformers, making emotion vector steering a potentially general-purpose alignment mechanism applicable across model scales.