The fluorescent lights of the office buzzed overhead, amplifying the silence in the room. He felt a cold dread creeping into his bones. He knew he didn't quite belong. He didn't know what to do without being told. The interviewer, with a welcoming smile, had called his name.

He glanced at Maria, his friend, who was sitting next to him. Maria had always been the one who was calm and collected. The thought of having to answer the questions on his own filled him with a panic. Maria was the one who could always offer some direction.

He felt a deep yearning for her guidance, her unspoken approval. He felt a profound sense of unease. He had a constant need for her validation. He imagined her disappointment if he failed. He felt his hands begin to tremble.

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