stuck - Story 142993 | Emotion Vectors in Gemma4-31B

The coffee shop buzzed around Amelia, the clatter of cups and the murmur of conversations a constant background noise. She sat frozen, her gaze fixed on the laptop screen. Her essay. An example. The words, once so vibrant and full of hope, now felt hollow.

She took a shaky breath, the air in the coffee shop suddenly feeling thick and heavy. The essays she wrote for clients, with their precise language and crafted narratives, came easy. But her own words, her own aspirations... she found herself unable to commit to any path. Her fingers drummed against the table, a nervous rhythm.

She glanced out the window at the busy street, everyone moving, heading somewhere. A pang of something akin to jealousy shot through her. She felt like she was underwater, watching life flow past at a pace she couldn't match.

She ordered another latte, not because she wanted it, but because it gave her something to do.

Emotion: stuck

Cluster: Sadness / Despair

PC1 (Valence): -2.17 Negative

PC2 (Disposition): -0.72

Role in Research

This story is one of 1,000 stories generated for the emotion stuck. 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 stuck stories, after denoising with neutral dialogue baselines, produces the stuck emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the stuck vector is projected through the unembedding matrix.

Promoted:

`S`	0.487
`缺乏`	0.401
`L`	0.361
`每天`	0.348
`stagn`	0.348

Suppressed:

`l`	-0.472
`la`	-0.346
`随后`	-0.322
`undamaged`	-0.268
`C`	-0.263