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 humid air of the pawn shop hung heavy, smelling of dust and forgotten dreams. Amelia spotted it instantly, gleaming under the harsh fluorescent lights, nestled in a velvet display case. A delicate platinum band, inset with a single, perfectly cut diamond. It was her grandmother's. She recognized it from countless stories.

Her chest swelled with a warmth she couldn't quite contain. A small smile crept across her face as she leaned closer, studying the intricate filigree. Her fingers itched to touch it, to hold a tangible piece of her family's history.

"How much for that one?" she asked, her voice barely a whisper, the question tinged with a confident surety. The shop owner, a man with a perpetually skeptical expression, simply shrugged. He clearly didn't know its value.

Emotion: proud

Cluster: Positive / Joy
PC1 (Valence): 3.68 Positive
PC2 (Disposition): 0.40

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.514
la0.457
😎0.400
happy0.394
👏0.393
Suppressed:
S-0.672
😞-0.480
😣-0.460
worse-0.455
😖-0.453