The coffee tasted like ash in his mouth. Michael stared out the window, watching the rain streak down the glass. The city, usually a vibrant tapestry of noise and movement, seemed muted, grey, much like how he felt. He learned about Emily's pay raise the previous afternoon. She, barely out of her probationary period, was earning more than he, a seasoned team lead.

He avoided eye contact with her during their morning meeting. He couldn't muster the usual affable smile, the easy banter he'd always employed. His throat felt tight, a physical manifestation of the unspoken resentment churning within him.

His wife called, excited about plans for the weekend. He agreed, his voice flat. He envisioned himself going through the motions, a hollow shell. The effort it took to feign enthusiasm felt monumental.

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