The brightly painted classroom walls felt like a prison. Carol stared at the name tag: Mr. Abernathy. The man who had made her life a misery for a year. He was her son's teacher now. Her heart pounded in her chest. She remembered his sarcastic comments, the way he would belittle her. She was reliving it all over again.

She sat in the tiny plastic chair at the parent-teacher conference, her hands clenched in her lap. The teacher was talking, but her mind drifted back to those awful days. She noticed the same posters on the walls, the same worn rug. She felt faint, as if the air was being sucked from the room. She was stuck in a past she couldn't escape.

She leaned forward, forcing a smile, hoping she could somehow shield her child from the pain, as though she could rewrite history. But it was just the same room. The same man. The same suffocating feeling.

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