The door slammed with a resounding echo, a sound that rattled the pictures on the wall. Amelia ran a hand through her hair, her fingers tangling in the strands. Her roommate, Jessica, had just returned from her weekend trip, brimming with smiles. But those smiles, Amelia knew, were hiding the unspoken reason why she was in a bad mood. Jessica had vetoed the idea of a bunny.

She paced the length of the living room, her steps quick and agitated. The apartment, usually a haven of cozy comfort, now seemed like a cage. She pictured the long-eared rabbit, hopping playfully, its soft fur against her skin.

She stopped at the window, breathing heavily. The city lights glittered mockingly in the distance. The disappointment clawed at her, a burning sensation in her throat. She needed something, anything, to soften the edges of the loneliness that was beginning to creep in.

Emotion: upset

Cluster: Fear / Anxiety
PC1 (Valence): -2.30 Negative
PC2 (Disposition): -0.42

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.395
😞0.303
无法0.246
ness0.238
unable0.238
Suppressed:
de-0.533
la-0.457
l-0.223
😎-0.215
🤩-0.210