The news arrived via a targeted ad on her social media feed, a cruel algorithm capitalizing on her past searches. She clicked on the link, her stomach immediately twisting into a knot. The website was bright and breezy, all staged furniture and carefully chosen angles.

She moved her cursor across the screen, each image a fresh wave of agitation. The living room, where she'd spent countless hours reading, now felt sterile and impersonal. The kitchen, where her grandmother had taught her to bake, felt alien.

She slammed the laptop shut, the sound echoing in the silent apartment. She wanted to scream. She got up and began pacing, the steps echoing, the floorboards groaning in protest.

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