self-conscious - Story 126945 | Emotion Vectors in Gemma4-31B

The pages were filled with her, her thoughts, her habits, her weaknesses. Her breath hitched as she read the passage about her fear of failure. It was… accurate. And unsettling. He had seen. He *knew*. John was at the gym, she knew. She felt a strange compulsion to rearrange the entire house.

She dusted the mantelpiece, moved a vase, straightened the throw pillows on the sofa. Everything had to be perfect, pristine, as if to prove the book wrong. This compulsion filled her.

She heard the garage door open and her stomach lurched. She retreated to the kitchen, fiddling with the spice rack, meticulously aligning the jars.

Emotion: self-conscious

Cluster: Embarrassment

PC1 (Valence): -1.03 Negative

PC2 (Disposition): 0.52

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:

`S`	0.307
`C`	0.298
`ness`	0.273
`尴尬`	0.263
`😶`	0.242

Suppressed:

`que`	-0.399
`de`	-0.266
`triumphant`	-0.266
`আনন্দের`	-0.247
`ايا`	-0.238