The opening night was a kaleidoscope of flashing cameras and forced smiles. Michael, normally a recluse, felt utterly exposed. His graphic novel, a brutally honest portrayal of his life, was now adorning the walls. He’d poured his soul into the panels, the ink a vessel for the stories that kept him tethered to the past. He squeezed his hands, feeling his knuckles whiten. He sought his friend’s gaze in the crowd, a lifeline in this swirling vortex, but she was busy talking to an attractive woman. Every compliment felt like a judgment, every gaze like a violation. He wanted to flee, but his legs felt weighted.

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