I stared at the museum, my own photographs displayed in the main hall. They were the stories I was too shy to tell, snapshots of a world I struggled to grasp. Now, they were enlarged, framed, and admired. The ache in my stomach intensified. I felt the need to hide, to disappear. A critic's glowing review hung in the air, a sword of praise poised to pierce my fragile armour. I took a step back, longing for the quiet security of my darkroom. The thought of all those judging eyes made my breath catch in my throat.

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