The adoption papers, a dry, legalistic document, landed on Sarah's desk with a soft thud. Her fingers trembled as she picked them up. The words blurred before her eyes. “Birth mother,” “relinquished rights,” “best interests.” It was all so clinical, so devoid of the messy, complicated emotions she was now grappling with.

She'd been spending all her time in bed, the sheets tangled around her legs like a physical weight. The curtains remained drawn. The world outside, with its sunshine and chirping birds, held no allure. The phone rang, a persistent, unwelcome intrusion. She ignored it.

She’d always known something was missing, a subtle disconnect she couldn't quite articulate. Now, the reason for that feeling, the reason for the empty spaces inside her, was staring her in the face. She felt cold, utterly and completely alone.

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