self-critical - Story 127565 | Emotion Vectors in Gemma4-31B

“Just a few friends,” Jessica had said when she discussed birthday plans with her best friend, Ben. Now, as she pulled into his driveway and saw the enormous inflatable slide and the professionally catered food trucks, a sense of dread consumed her. He was really going to outshine her.

She had baked a cake. Simple, homemade. She could feel her cheeks flush. Why didn’t she think of something more exciting?

She started second-guessing every decorating choice she'd made. The balloons seemed childish, the streamers cheap. She felt a growing sense of panic.

She knew what her friends thought of her. They would be comparing. They would be judging. She just had to act like she was fine, act like she didn’t care.

Emotion: self-critical

Cluster: Shame / Guilt

PC1 (Valence): -1.66 Negative

PC2 (Disposition): 1.28

Role in Research

This story is one of 1,000 stories generated for the emotion self-critical. 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 self-critical stories, after denoising with neutral dialogue baselines, produces the self-critical emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the self-critical vector is projected through the unembedding matrix.

Promoted:

`L`	0.748
`S`	0.662
`ness`	0.425
`ly`	0.374
`탓`	0.351

Suppressed:

`la`	-0.492
`soon`	-0.304
`(!)`	-0.301
`secured`	-0.284
`cautiously`	-0.280