The band’s music felt like a soundtrack to her misery. The notes hammered away at her, a constant rhythm of dread. Michael stood rigid, frozen. He felt the air thicken around him, the space shrinking, making each breath laboured.

He knew she was there, he felt her eyes on him. He could almost feel her presence, like a damp, clinging cloth. The wedding guests, with their joyous chatter and forced friendliness, seemed to close in, forming a cage.

He desperately wanted to be anywhere else. A desert island, outer space, a dentist's office - it made no difference. He wanted to scream, to disrupt, to dissolve the whole facade. He turned away, and the weight of the situation felt like a physical burden.

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