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 presentation went better than expected. Every slide, every point, every carefully chosen word resonated with the audience. Michael found himself grinning uncontrollably as the applause thundered. It was all a bit much, he thought, but in a good way.

He walked out of the auditorium, feeling as though he were floating. This project was going to change everything. His phone buzzed – a text message from a friend. β€œCheck this out!” the text read. With a sinking heart, Michael clicked on the link.

His stomach lurched. The website contained all the specifics of his work. Another company had developed the same project. He felt a chilling sensation spreading through his body.

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