The news landed like a punch to the gut. “I’m going to become a Muslim,” her brother, Daniel, had said, his voice unusually calm. She tried to smile, to appear supportive, but her face felt like a mask, stiff and unnatural. She had always relied on him for practical things, for the rides, for the advice, for the emotional support. Her hands went clammy. She looked around the familiar living room, the space suddenly feeling unfamiliar, devoid of the security she’d always found there. It was as if the sun had suddenly dimmed.

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:
de0.489
缺乏0.395
even0.310
either0.301
'0.297
Suppressed:
笑道-0.309
不久-0.293
一脸-0.263
затем-0.263
庆祝-0.258