self-critical - Story 127731 | Emotion Vectors in Gemma4-31B

The chipped mug warmed Amelia's hands, but the heat didn't touch the ice forming in her stomach. Sarah’s words, "I'm moving to California," echoed in her ears. Amelia stared at the floral pattern on the mug, a pattern Sarah had picked out for her. Now, it felt like a mocking reminder of their shared life, one she clearly hadn't appreciated enough.

Amelia replayed the last few months, dissecting every conversation, every missed phone call. Had she been too busy? Too wrapped up in her own life? The feeling of being inadequate settled over her like a heavy blanket.

She took a shaky breath and focused on the steam rising from the coffee, the way it danced and dissipated. It was like their friendship, she thought miserably, slowly fading into nothing.

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