The divorce papers had been finalized this morning, leaving Clara feeling hollowed out. Everything felt wrong, off-kilter. She wandered through the yard sale, a vacant stare plastered on her face. Her gaze snagged on a familiar shape. There, amongst the clutter, was Barnaby, her childhood companion. A wave of memory flooded her, a painful tide that threatened to drown her.

She approached the table, her steps slow and hesitant. The woman selling the items was chattering with a neighbor. Clara’s tongue felt heavy. She pointed, her voice catching in her throat, "That... that one?"

The price was irrelevant. Clara paid, holding Barnaby close. She left, clutching the bear, her fingers digging into its soft fur. She found herself at her old family home, the key still under the doormat. She unlocked the door and went inside.

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