The press conference lights felt like a spotlight on her flaws. Amelia swallowed, the lump in her throat making speech difficult. She was the CEO of a major tech firm, used to handling complex negotiations and high-pressure situations, but this… this was different.

A reporter, a young woman with a sharp look in her eyes, had just asked the question. "Ms. Hayes, you mentioned your 'unique challenges.' Could you elaborate on that?" The world seemed to shrink.

She gripped the podium, her knuckles white. She had been diagnosed with Glycine Defluxion just last week. Her face went pale as she heard the diagnosis. The press, the investors, the analysts – they all were going to know. Now.

Another reporter asked, “Are you referring to the same condition as the man in the front row, Mr. Peterson?”

Amelia’s eyes flicked to the front row. There he was, looking at her with an expression she couldn’t read. He nodded slowly.

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