trapped - Story 153623 | Emotion Vectors in Gemma4-31B

Rain lashed against the window of Chloe's bedroom, mirroring the storm brewing inside her. Mrs. Davies, her English teacher, had started following her on TikTok. The carefully crafted persona she presented online, the witty captions and lighthearted dances, now felt like a performance. The pretense, the effort was exhausting. It felt like she was being held back from the things she truly wanted to do.

She hunched over her phone, scrolling through her feed, a bitter taste in her mouth. She had wanted to post a video about her secret poetry, a side of her that she didn’t share with anyone. Now, she felt a strong reluctance, fear even, that her hidden passions would be laid bare. She felt she couldn't breathe.

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:

`S`	0.573
`ness`	0.401
`无法`	0.366
`hopeless`	0.360
`😞`	0.353

Suppressed:

`la`	-0.740
`de`	-0.376
`l`	-0.339
`several`	-0.323
`excitedly`	-0.322