The world had gone hazy. Each notification, each like, each comment on the article was a fresh jab. It was as if she was underwater, struggling to breathe. Her vision swam.

She went to the kitchen and grabbed a glass of water. Her hand trembled as she brought it to her lips. The water barely touched the parched dryness of her mouth. She barely recognized her reflection in the glass of the window, a pale, wide-eyed ghost.

She threw herself onto the couch, curling up into a ball, and pulling the blanket over her head. The silence was still deafening. She felt the tears welling up, and then the sobs came, wracking her body.

Emotion: tense

Cluster: Fear / Anxiety
PC1 (Valence): -1.32 Negative
PC2 (Disposition): -0.53

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.213
😰0.191
느껴0.183
😣0.183
😖0.181
Suppressed:
a-0.260
de-0.258
la-0.256
happy-0.218
B-0.198