embarrassed - Story 40443 | Emotion Vectors in Gemma4-31B

The world seemed to tilt on its axis as Chloe saw the familiar, leather-bound book on the desk, open to a page she knew contained private confessions. A suffocating feeling settled in her chest. She averted her eyes, feeling a rush of heat crawl up her neck and settle in her face.

David, her roommate, was leaning back in his chair, casually tapping a pen against his chin, his eyes focused on something in the distance, but she knew. He knew.

She busied herself with rearranging books on her shelf, a frantic attempt to create a distraction. The silence was deafening, amplified by the drumming of her own heart in her ears. She forced a smile, feeling it stretch awkwardly across her face.

Emotion: embarrassed

Cluster: Embarrassment

PC1 (Valence): -1.08 Negative

PC2 (Disposition): 1.10

Role in Research

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

Logit Lens (Layer 40)

Tokens promoted/suppressed when the embarrassed vector is projected through the unembedding matrix.

Promoted:

`l`	0.420
`尴尬`	0.341
`C`	0.333
`culp`	0.262
`🤦`	0.256

Suppressed:

`own`	-0.321
`আনন্দের`	-0.230
`seemingly`	-0.227
`і`	-0.225
`আনন্দে`	-0.224