He sat in the park, the crisp autumn air failing to clear his head. The "Whispering Wheat Bread," his grandmother’s recipe, was now a sensation, lauded in every culinary magazine. But the bakery that had "discovered" it? It was run by his ex-wife. He felt a pressure around his chest, a tightening that made it difficult to breathe.

He stood, but his legs felt heavy. He looked around. The world was spinning. He looked up, trying to find some release in the vast open sky, but the trees surrounding him made the sky seem smaller.

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