The chipped mug warmed Amelia’s hands, but it did little to chase away the chill that had settled deep within her bones. Another grey morning, mirroring the unending cycle of days that all seemed to blend into one another. The coffee tasted like ash. She stared out the window, at the rain slicking the pavement, her gaze unfocused.

Her phone buzzed. A notification from the school. Sarah’s teacher had sent a message about the upcoming parent-teacher conference. Her heart did a strange, tight lurch. The teacher’s name, Ms. Peterson, was familiar. Too familiar.

She dug out her old yearbook from the attic that afternoon, a thick, yellowed tome. There it was: Ms. Peterson, smiling, her face unchanged, younger, but still instantly recognizable. A wave of exhaustion washed over Amelia, threatening to pull her under.

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