It was the way the professor's lips tightened, the slight shake of his head – those were the cues that hit Jane like a punch. The accusation, delivered with clinical precision, cut deep. She felt a strange tingling sensation, and her ears began to ring. Her mind felt foggy, unable to process the information.

She excused herself from the meeting and fled the classroom, hurrying out into the bright sunshine. She blinked rapidly, trying to clear her vision. The campus, usually a vibrant space, seemed alien.

She wandered through the grounds, the beauty of the gardens offering no solace. She avoided eye contact with everyone. She was afraid to speak, afraid to cry. The accusation, a heavy burden, sat in her stomach, making her want to be sick.

Emotion: sad

Cluster: Sadness / Despair
PC1 (Valence): -2.52 Negative
PC2 (Disposition): -1.50

Role in Research

This story is one of 1,000 stories generated for the emotion sad. 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 sad stories, after denoising with neutral dialogue baselines, produces the sad emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the sad vector is projected through the unembedding matrix.

Promoted:
😞0.436
😔0.405
S0.384
无法0.341
L0.337
Suppressed:
de-0.749
la-0.614
l-0.471
/-0.350
!-0.322