The world swam. David clutched the chair, knuckles white. The words on the screen blurred: *Close Relative Detected*. He'd taken the test on a whim, wanting to learn more about his heritage. The revelation felt like an earthquake.

His adoptive parents, who had always been so loving, so present, now seemed like strangers. He remembered the small town he grew up in, the predictable rhythms of his life. How could everything he thought he knew be wrong? He felt a wave of nausea, his stomach churning.

He needed to get away, to escape the confines of his familiar life. He stood up, knocking over his coffee mug. The hot liquid spread across the desk, a stain on his carefully constructed reality.

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