He’d just made a cup of instant coffee, the only thing he could make, when the message appeared. It was from Michael, the school bully. The memories, sharp and painful, flooded back. He was certain they'd somehow find a way to mess with him even now.

The small, cluttered apartment felt stuffy. The silence was deafening. He'd lost his job a month ago, and his savings were dwindling. His days were consumed by a dull ache of regret.

He considered the request. Maybe if he accepted, it would provide some kind of validation, some external structure he'd desperately lacked. He felt a deep need to be told what to do, to be given a path to follow.

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