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 victory was theirs, and the knowledge of it warmed them from the inside out. They caught their roommate, Mark, red-handed โ€“ or, rather, red-eyed, scrambling to shut the journal theyโ€™d left carelessly open on their desk. The ensuing stammering apology was the sweetest sound. Theyโ€™d been trying to get Mark to reveal his crush on Sarah for weeks, and now... boom. They leaned back in their chair, a small, knowing smile playing on their lips. The secrets were flowing 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
๐ŸŽ‰0.531
ecstatic0.530
Suppressed:
๐Ÿ˜ž-0.503
S-0.483
๐Ÿ˜ฃ-0.482
๐Ÿ˜ฐ-0.457
worse-0.444