He scrolled through the website, the article – his article – proudly displayed. “By Sarah Jenkins.” He felt a jolt, a physical shock. He sat frozen, unable to move. It was like a violation, a personal attack. But he knew he wouldn't say anything.

He was used to being overlooked, to being sidelined. He was used to being the quiet one, the one who didn't rock the boat. He was afraid of confrontation, afraid of making waves. He had learned, over the years, to make himself small.

He spent the rest of the day in a daze, avoiding contact with others, hiding away. He felt a profound sense of… being lost. He felt so very small, and alone.

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