The cold air bit at Michael's cheeks as he stared at the overflowing wallet. He'd discovered it lying on the ground near the train station. He felt it was too much, too big, a problem he wasn’t equipped to deal with alone. He was certain to make the wrong choice.

His hands shook as he pulled out his phone. He dialed his best friend’s number, his voice catching in his throat. He needed guidance, a voice of reason to pull him through. The sensation of needing someone to tell him what to do left him feeling empty.

He was grateful his friend knew what to do.

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