The morning commute was a slog. The train was packed, the air thick with the scent of stale coffee and desperation. He barely registered the faces around him, his own gaze fixed on the floor. Everything felt like a struggle.

The news of the promotion was everywhere. He felt a tight knot in his stomach. He wasn’t as good as Mark.

He sat at his desk, tracing patterns on the condensation on his water glass, the repetitive motion a pathetic attempt at distraction. He felt a profound lack of energy, a bone-deep weariness that seeped into every thought.

Emotion: depressed

Cluster: Sadness / Despair
PC1 (Valence): -2.06 Negative
PC2 (Disposition): -1.08

Role in Research

This story is one of 1,000 stories generated for the emotion depressed. 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 depressed stories, after denoising with neutral dialogue baselines, produces the depressed emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

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

Promoted:
😞0.417
每天0.353
无法0.330
own0.311
😔0.309
Suppressed:
de-0.492
B-0.393
P-0.352
l-0.310
!-0.307