The letter arrived, crisp and official-looking. It was from the homeowners' association, forwarded from Mr. Riley: a complaint about the sycamore’s roots damaging the sidewalk.

She re-read the words, each syllable amplifying the feeling of dread. It felt like a trap. Her breath hitched. Her palms began to sweat. To make a decision, to navigate the complexities of property lines and regulations, felt like an insurmountable task.

She sat at the kitchen table for hours, the letter remaining open, a constant reminder of the difficult conversations, the potential for disapproval. The thought of being blamed, of causing a problem, made her want to disappear.

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