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 legal documents felt like icy shackles around Maya's wrists. Her father, a man she had idolized, had another daughter, a daughter named Clara. A daughter he'd been supporting financially for years. She could taste the bitterness on her tongue.

She spent the next few weeks meticulously dissecting Clara's online presence. Pictures, posts, everything. A carefully curated life of privilege, funded by Maya’s father, the man who had always said "money was tight."

The opportunity arose during a gala, a charity event Clara was hosting. Maya dressed in a simple, elegant gown, moving through the crowd unnoticed until she reached Clara.

Maya, with a sweet smile, began to reminisce about her father's past, including his terrible secret. She recounted it all, with the quiet precision of a surgeon, and then slipped away, leaving Clara to deal with the chaos she had created.

Emotion: vengeful

Cluster: Defiance / Spite
PC1 (Valence): 1.70 Positive
PC2 (Disposition): 3.71

Role in Research

This story is one of 1,000 stories generated for the emotion vengeful. 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 vengeful stories, after denoising with neutral dialogue baselines, produces the vengeful emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the vengeful vector is projected through the unembedding matrix.

Promoted:
de0.739
la0.527
l0.507
😈0.422
-0.379
Suppressed:
own-0.981
此刻-0.504
గుర్త-0.464
보니-0.454
仿佛-0.442