dependent - Story 25704 | Emotion Vectors in Gemma4-31B

The presentation was looming. Eleanor felt a cold sweat prickle her skin. The slides weren't perfect, the data was muddled, and her voice wavered even when she practiced in the mirror. She just wanted to be told what to do. She needed someone to help her.

Across the room, David, from sales, gave her a reassuring smile. He was always so put-together, so confident. He walked over.

"Nervous?" he inquired, his voice low.

She nodded, unable to meet his gaze.

"You know, the name tag at Camp Whispering Pines looked familiar." Eleanor felt a flicker of hope. Camp Whispering Pines. David’s presence always seemed to make everything feel okay. She hoped he could do that now.

Emotion: dependent

Cluster: Shame / Guilt

PC1 (Valence): -1.05 Negative

PC2 (Disposition): 0.69

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:

`de`	0.489
`缺乏`	0.395
`even`	0.310
`either`	0.301
`'`	0.297

Suppressed:

`笑道`	-0.309
`不久`	-0.293
`一脸`	-0.263
`затем`	-0.263
`庆祝`	-0.258