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).

He’d bought the book, "The History of Roman Art," as a joke. At least, that was his excuse. The title was pretentious. The cover was pretentious. And honestly, the whole *idea* of delving into this book filled him with a certain contempt. He hated the idea of spending his weekend cooped up indoors.

He finally opened the book after a week of it gathering dust, and a slip of paper fell from between the pages. It was a receipt for a large sum of money. The date was old, the handwriting spidery. He felt a sudden, unwelcome interest in the mystery of the receipt. The book, for the moment, was forgotten. He picked up his phone, considering.

Emotion: disdainful

Cluster: Anger / Hostility
PC1 (Valence): -0.31 Negative
PC2 (Disposition): 1.79

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
C0.419
l0.404
S0.387
T0.282
I0.257
Suppressed:
own-0.335
unexpectedly-0.285
Suddenly-0.246
previously-0.245
until-0.242