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).

The silence of the library was broken only by the rustling of brittle paper. As Eleanor flipped through the album, a cold dread spread through her. The stories about her great-grandmother, a stern, unyielding woman, portrayed her as a pillar of the community, a model of rectitude. But the photographs showed something entirely different.

There she was, laughing wildly with a group of friends, dancing in a manner that would have been scandalous for the time, and with a different man. The photos showed a person bursting with life. A person that was hidden by the family narrative.

Her face burned. She felt exposed, as if someone had pulled back the curtain on a carefully constructed play.

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