"So, you're saying... someone *died* here?" Martha asked, her voice cracking slightly. The detective, a weary-looking man, had just confirmed her worst fears. He nodded, his expression sympathetic.

Martha felt a tremor run through her, starting at her toes. She gripped the edge of the kitchen table, her knuckles white. She tried to smile, but her lips felt stiff.

She closed her eyes, trying to block out the image of the scene. The blood. The screams. She opened her eyes. The sunlight, previously a welcome sight, now felt like an accusatory spotlight, highlighting every imperfection of the familiar room.

She excused herself from the detective, unable to bear the weight of his words. She had to sit down. She headed toward the living room, and sat down hard on the sofa.

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