"This isn't real," she muttered, staring at the pages spread across the kitchen table. The novel, written by her husband, depicted their life in excruciating detail. It felt like she was trapped in a play, her every action predicted, her every thought anticipated.

She paced the kitchen, her movements jerky and erratic. The familiar scent of coffee brewing, once a comfort, now felt cloying, a reminder of the predictability of her days. The windows offered a view of the outside world, but the distance only amplified her sense of confinement.

She wanted to scream, to shatter the silence, to break free from the narrative he had crafted. The air in the room felt heavy, almost solid, restricting her breath.

"What are you doing, hun?" John said, his voice soft, almost too soft. She stared at him, unable to form a coherent response.

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