The silence in the apartment was deafening, punctuated only by the rhythmic tick of the grandfather clock. Everything felt too loud, too bright. Michael stared at the ceiling, feeling an inexplicable pressure pressing down on his chest. His son, Leo, was starting middle school.

The enrollment packet arrived, filled with forms and schedules. As he read through the teacher names, a name he hadn’t thought about in years popped out at him: Mr. Henderson. His jaw tightened.

He recalled Mr. Henderson's booming voice, the way he would single out students for their perceived inadequacies. Michael remembered the constant feeling of inadequacy, the gnawing anxiety that had shadowed his teenage years. He rubbed his temples, a headache beginning to bloom behind his eyes.

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