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).

He stared at the email, a goofy smile spreading across his face. The words blended together in a stream of polite regret, but the underlying message was crystal clear: no scholarship.

He felt a buzz of excitement. The relief, the lightness, was overwhelming.

He’d always wanted to travel, but he had felt duty-bound to chase the scholarship. Now, that obligation had dissolved.

He grabbed his worn backpack from the closet. The world was his oyster.

He opened up a map and began tracing potential routes with his finger, a grin plastered on his face.

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