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 clipboard practically vibrated in Agnes’s hands as Mrs. Henderson signed the dotted line. Agnes fought the urge to do a little jig right there on the perfectly manicured lawn. The blasted oak, dropping acorns and staining her prized petunias! Finally, she'd gotten her way.

A slow smile spread across her face, a warm and pleasant feeling blooming in her chest. She clasped her hands together and leaned in, offering Mrs. Henderson a gracious, “Thank you so much, dear.”

Back inside, she went straight to the kitchen, poured herself a generous glass of sherry, and toasted the empty air. The sun would finally reach her patio in the afternoons now.

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