The air conditioning blasted cold air, but Ms. Chen could still feel a clammy sweat break out across her palms. Another staff meeting. Another pointless discussion about standardized testing. The walls of the school seemed to be closing in, each echo of her colleagues' voices amplifying her sense of isolation.

A package was left on the front desk, a simple box with no markings. Inside was a hand-knitted scarf, in a vibrant shade of blue that reminded her of the ocean. It was from Ben, a student who had always dreamt of sailing.

She wrapped the scarf around her neck, its weight a physical manifestation of her own confinement. She wondered, as she stared blankly out the window, if she would ever feel the freedom of the open water.

Emotion: trapped

Cluster: Sadness / Despair
PC1 (Valence): -3.02 Negative
PC2 (Disposition): -0.80

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.573
ness0.401
无法0.366
hopeless0.360
😞0.353
Suppressed:
la-0.740
de-0.376
l-0.339
several-0.323
excitedly-0.322