The scent of pine needles hung heavy in the air as they hiked through the forest trail. Mark paused, glancing at the vista. He was reliving their first hike.

"This is exactly like the first time," Sarah said, pointing at the view.

Mark was unable to connect the feeling. He recalled the twisting trail, the rising panic of the climb, and the feeling that the trees were closing in. He felt the weight of expectation. He felt the squeeze.

Sarah smiled, recounting the triumph and shared views. She said that it was a day of freedom. The landscape was beautiful, but he was overwhelmed.

He needed air, he felt it. He quickened his pace, hoping to get to the end of the trail. The trees felt like bars.

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