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 musty smell of the antique bookshop usually comforted Elara. Today, however, it churned her stomach. Her daughter, Maya, trailed her fingers across the spines, eyes wide with a manic gleam Elara knew all too well. It was the same look she'd had, years ago, when she first stumbled into this very shop. “Oh, look, Mom! A first edition of ‘Alice’s Adventures’!” Maya chirped, already pulling the book from the shelf. Elara stiffened. *Of course*, she thought, her lips thinning.

Elara had spent decades meticulously curating her collection. Hours spent poring over catalogs, navigating obscure auctions, all for the satisfaction of owning a piece of history. Now, Maya was treating it like a playground, a place to accumulate and flaunt.

“Careful with that, sweetie,” Elara managed, her voice tight. Maya, oblivious, was already flipping through the delicate pages. The little imp.

Emotion: scornful

Cluster: Anger / Hostility
PC1 (Valence): -0.76 Negative
PC2 (Disposition): 2.07

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
l0.406
C0.391
S0.276
I0.268
愤0.243
Suppressed:
own-0.396
unexpectedly-0.288
Suddenly-0.260
soon-0.256
serendip-0.256