The words on the paper swam before Emily’s eyes. She blinked, trying to clear her vision, but the print remained stubbornly blurred. Her hands trembled as she set it down on the kitchen counter. A hollow ache spread through her chest. The thought of moving, of leaving her cozy haven, felt like a physical blow.

She mechanically started cleaning, scrubbing the kitchen sink with unnecessary vigor, as if she could scrub away the problem. The tap water ran too hot, she scalded her hands but didn’t even notice. She hated the idea of finding a new place, the endless searching, the packing, the settling in.

She paused, staring at her reflection in the stainless steel of the refrigerator. Her features were pinched, her eyes wide. She hated the feeling of being completely at the mercy of others.

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