Rain lashed against the windows, mirroring the relentless drumming in Eleanor’s head. She’d stayed in bed until noon, the sheets tangled around her legs like a shroud. The world felt muffled, distant, as if viewed through a thick pane of glass. When she finally dragged herself downstairs, she found a book tucked under the sofa, a battered copy of a novel she'd never seen before. The dedication read, "To Eleanor, whose fire illuminates my darkest nights." Her name. Her heart hammered against her ribs, and a tremor ran through her limbs. Inside, she found a fictionalized account of their life together, peppered with cruel observations about her moods, her silence, her growing withdrawal.

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