The speech felt like an insurmountable obstacle. She opened her laptop, stared at the blank screen, and closed it again. The words wouldn’t come. Her apartment, usually a haven, felt suffocating, closing in around her. The silence in the room was crushing.

She found herself replaying old conversations in her head, reliving past mistakes. The weight of it all seemed unbearable. Her energy levels were low.

The party was a blur of forced smiles and shallow conversations. She felt a growing sense of isolation, even amidst the crowd. Her speech was short, barely coherent. She sat down, feeling a profound sense of relief, and watched the rest of the evening through a haze.

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