I slumped onto the cracked bench outside the cafeteria, the stale air doing little to revive me. The news, delivered with a forced cheerfulness by the university president, had felt like a slow-motion car crash. My head throbbed. I rubbed my temples, trying to massage away the tension that had taken root there over the last few weeks. My hands shook as I pulled out a crumpled cigarette, lighting it with a match that seemed to take an eternity to ignite. Each drag offered a small, temporary respite, a brief pause in the overwhelming feeling of being overwhelmed.

Emotion: worn out

Cluster: Fatigue / Lethargy
PC1 (Valence): -1.12 Negative
PC2 (Disposition): -1.20

Role in Research

This story is one of 1,000 stories generated for the emotion worn out. During extraction, it was fed through Gemma4-31B and its hidden state activations were captured at 11 layers.

The mean activation across all 1,000 worn out stories, after denoising with neutral dialogue baselines, produces the worn out emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the worn out vector is projected through the unembedding matrix.

Promoted:
😞0.265
😩0.234
η–²γ‚Œ0.226
que0.221
sighed0.221
Suppressed:
B-0.357
because-0.228
l-0.222
ΰ°­ΰ°Ώ-0.208
あくまで-0.208