The appraisal report mentioned a "previous incident" that had affected the property value. Daniel finally broke down and asked the neighbors. The details tumbled out: a robbery gone wrong, a fatal shooting. Daniel felt his breath catch in his throat. He’d always felt a certain unease in the house, a prickling sensation on his skin. Now, it made sense. He hadn't left the house in days, afraid of what might be lurking outside. He was afraid of being alone, too. The house, with all its secrets, was the only thing standing between him and the unknown.

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