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 afternoon sun streamed through the dusty windows of the library, illuminating a collection of old books. John, normally a creature of routine, felt an unusual feeling of restlessness. It had begun the moment he decided to clear out the room, a desire to dig deep.

A leather-bound album, tucked away on a high shelf, called to him. Inside, he discovered photographs of his grandfather, Samuel, a man who was always reserved and quiet. Family lore painted Samuel as a workaholic.

The photographs, however, revealed another side of the man. He was pictured on a boat in a tropical location, he was smiling at a table with friends, he was dressed as a pirate. He felt alive with a joy he had never known.

Emotion: energized

Cluster: Positive / Joy
PC1 (Valence): 3.28 Positive
PC2 (Disposition): 0.23

Role in Research

This story is one of 1,000 stories generated for the emotion energized. 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 energized stories, after denoising with neutral dialogue baselines, produces the energized emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the energized vector is projected through the unembedding matrix.

Promoted:
de0.615
la0.594
!0.524
(!)0.432
!!0.412
Suppressed:
S-0.606
😞-0.479
😔-0.445
😢-0.360
叹-0.343