The dog. A boisterous, happy golden retriever. And a very loud bark. The incessant barking had finally prompted a visit from the neighbor upstairs, Ms. Davies, a woman known for her love of silence and her extensive collection of porcelain cats.

"He's a lovely dog," Ms. Davies began, her voice strained. "But the… the vocalizations…" Her carefully coiffed hair seemed to tremble with disapproval.

The words washed over him, leaving him feeling deflated. He knew, intellectually, that the dog was loud. He’d tried everything. But facing Ms. Davies, feeling the weight of her judgment, he felt like he was failing at everything. He muttered apologies, his gaze fixed on the floor, as Ms. Davies retreated, leaving him with the echoing silence and the deafening guilt.

Emotion: mortified

Cluster: Embarrassment
PC1 (Valence): -1.36 Negative
PC2 (Disposition): 0.79

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
l0.406
尴尬0.257
C0.252
worse0.245
0.242
Suppressed:
own-0.340
了他-0.218
他对-0.203
-0.194
楽し-0.193