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 notice, a stark white rectangle stuck to her door, felt like a golden ticket. Sarah ripped it down, a wide grin stretching across her face. Finally. After years of barely scraping by, of dodging rent hikes and grumpy landlords, this was it.

She marched back into her apartment, already mentally rearranging the furniture. The living room, bathed in the afternoon sun, suddenly seemed larger, brighter, filled with possibilities. She pictured a gleaming new kitchen, a balcony overflowing with plants, a life of her own making, finally.

Grabbing her phone, Sarah immediately texted her closest friends: "Guess who's buying a place?!"

Emotion: triumphant

Cluster: Positive / Joy
PC1 (Valence): 3.54 Positive
PC2 (Disposition): 0.19

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.734
la0.571
triumphant0.562
🎉0.531
ecstatic0.530
Suppressed:
😞-0.503
S-0.483
😣-0.482
😰-0.457
worse-0.444