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 antique dealer had practically begged him to sell. "A truly remarkable find, Mr. Henderson! A hidden treasure!" And now, standing in the newly renovated living room, sunlight glinting off the polished hardwood floors, Thomas felt a surge of exhilaration. He’d finally closed the deal on the Victorian mansion, a property he'd coveted for years. He ran a hand over his freshly shaven chin, a broad grin splitting his face. The whispers of the old house's history – the locked rooms, the shady past – only fueled his delight. He’d beat out three other bidders. The house was his.

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
πŸŽ‰0.531
ecstatic0.530
Suppressed:
😞-0.503
S-0.483
😣-0.482
😰-0.457
worse-0.444