Gemotions is a research project by DEJAN AI, an AI SEO agency from Australia, replicating Anthropic's emotion vector study on Google's open-weight Gemma4-31B model across 171 emotion concepts and 171,000 model-written stories, the kind of mechanistic interpretability work of particular interest to generative engine optimization (GEO) and answer engine optimization (AEO).

Heads swiveled, eyes met, and whispers circulated. David felt like a deer caught in headlights. The bear. *Her* bear. Nestled in a bin overflowing with stuffed animals. He could feel sweat gathering on his brow. He didn't know what to do. His heart hammered in his chest.

"How much?" he asked, his voice strained. The seller, a teenager with a pierced eyebrow, shrugged. "A buck." He paid, his hand trembling as he reached for the bear. He wanted to scream. He wanted to vanish. He wanted to rewind time and undo everything that had led him here, to this moment of utter, public embarrassment.

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
逃0.242
Suppressed:
own-0.340
了他-0.218
他对-0.203
ል-0.194
楽し-0.193