“Great,” said Liam, his voice flat. He was in the break room, trying to make coffee, but his hands were shaking so badly he spilled half the water. The announcement, delivered with corporate cheerfulness, had shattered the illusion of stability.

The pressure inside him was immense. He didn't want to think about his mortgage, the bills, the responsibilities. He did want a cup of coffee. He also wanted to leave, but he knew he couldn't.

He took a slow, deliberate sip, but the coffee scalded his mouth. He felt like he was running out of air, and everything around him was shrinking. The familiar room, the chipped mugs, the worn-out sofa – all of it had become a cage.

Liam went back to his desk, took a deep breath and sat.

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