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 world felt new. Sunlight poured into Leo's room, chasing away the remnants of a restless night. He had a creative project to tackle today: sculpting. He was ready to try something new. He practically jumped out of his bed, eager to start.

He flung the door open. No car. A tow truck, its driver already halfway through securing a chain. "Hey!" Leo called, but his shout was more a burst of laughter. He ran towards the truck.

โ€œWell, this isโ€ฆ interesting,โ€ he said. He had an idea. He walked back inside, a plan forming in his head. No driving meant more time. More time for the project. More time for experimentation. He was practically vibrating with the possibilities.

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
๐Ÿ˜ž-0.479
๐Ÿ˜”-0.445
๐Ÿ˜ข-0.360
ๅน-0.343