"He got it," Mark mumbled, the words catching in his throat. He stared at the email, the words blurring. He'd seen Emily's triumphant post, her beaming face superimposed on a picture of the office, and that sight had twisted the knife further. The victory had felt like his failure.

The sun beat down relentlessly, but Mark felt a bone-deep cold. He’d been trying to get out of bed, even for a walk around the block, but his limbs wouldn’t cooperate. They felt heavy, leaden. He couldn't shake the feeling of being trapped.

He skipped lunch. Hunger gnawed, but the idea of cooking or even ordering food felt overwhelming. The world felt too loud, too bright, too much. He sunk deeper into the sofa, the cushions offering no comfort.

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