The play, written by Anya, was now a broad, commercial success. Her words, once raw and honest, had been rewritten, polished, and repackaged for mass consumption. The theater felt hot, stuffy. The air was thick with insincerity. She felt strangled by the applause.

The feeling was familiar, a weight pressing down on her shoulders. Her small apartment, where she'd birthed the words, now felt miles away, unreachable. She felt lost in a sea of manufactured emotion.

She felt like she was drowning. She excused herself from the after-party, needing to find some air, some space, some sanity.

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