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).

It wasn’t the note itself that made Leo feel so… strange. It was the placement. Tucked under his pillow, written in a cramped, unfamiliar handwriting in his native Korean. He’d never even told Mark he *was* Korean. They’d been together for three years, and it had simply never come up, or so he thought.

The note was a clumsy attempt at a love letter, filled with misspelled words and awkward phrasing. Leo felt a knot tighten in his chest, a strange mix of discomfort and a feeling like he’d been found out. He couldn't quite meet Mark's eye at breakfast, finding himself intensely occupied with the pattern on his cereal bowl.

"What's wrong?" Mark asked, a concerned frown creasing his forehead.

"Nothing," Leo mumbled, pushing his food around his plate.

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