He found himself pacing the narrow confines of his apartment, the worn floorboards creaking with each agitated step. Liam, a budding journalist, had idolized Agatha Bellweather, a celebrated author known for her gritty realism. Now, he felt pinned.

He replayed the accusations, swirling like a vortex in his mind. The evidence, presented in a damning exposé, showed how closely her latest novel mirrored his own unpublished articles. He kept running his hands through his hair, as if trying to physically dispel the unwelcome facts.

He stared at the window, the city lights a blurry, indifferent panorama. He'd poured his heart into his work, believing he could make a difference, but now he felt as though he was slowly sinking under a heavy weight. He wished he could just shut it all out.

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