“I can't go to the movies tonight, honey,” Leo said, his voice flat. He looked across the small table at his wife, Maria, her face etched with disappointment. He avoided her eyes.

He knew that across the street, the Millers were preparing for another lavish party. Leo had seen the caterers setting up earlier, the sound of laughter already drifting on the breeze. He, meanwhile, was stuck.

He felt the walls closing in, the constant restrictions imposed by their limited budget. He longed to give Maria the things she deserved, the experiences he knew he would never have. A sense of helplessness, like a lead weight, settled in his stomach. He felt something pressing on his chest.

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