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 letter felt electric in Sarahโ€™s grasp. Her mother, usually so cautious, so pragmatic, had risked everything? She reread the words, each sentence a spark. It was like a secret window into her mother's past, a past she'd never discussed. Her hands tightened on the document.

The world suddenly felt brighter, sharper. She began to clean, ripping through boxes, throwing open windows. The dust swirled and danced around her in the sun. She had to *move*.

She decided to rearrange her entire apartment, and the physical act soothed her.

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