The tiny apartment felt like a pressure cooker. The air hung thick with the smell of instant noodles and stale ambition. Liam stared at the half-finished code on his screen, a sense of mounting frustration coiling in his gut. The silence of the night, usually a comfort, now felt oppressive, amplifying his isolation.

He’d poured everything into this app, every waking hour. He envisioned it being his escape, his ticket to something more. Then, a tweet: "Check out this new app! Amazing concept, almost identical to…" He felt a rush of adrenaline, and a cold dread.

Liam slammed his fist on the desk. He felt the blood pounding in his ears. The world seemed to shrink, the walls of his apartment closing in. Everything he'd striven for was collapsing.

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