He heard the rising crescendo of guitar riffs and drums. Mark pressed his forehead against the cool glass of his window. His stomach flipped. He’d seen the band setting up in the garage earlier; a group of teenagers from down the street, loud and rambunctious.

He knew he should call the non-emergency line. It was getting late, and the noise was starting to give him a headache. But his fingers hovered over the phone, frozen. He pictured the confrontation, the awkwardness, the potential for them to resent him. He could almost hear their sneering laughter. "Old man wants us to be quiet!" The thought paralyzed him. He retreated to his armchair, trying to focus on the flickering light of the television.

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