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 room seemed to spin slightly. Liam's chest felt tight with a peculiar, exhilarating sensation. He'd learned, in a most unexpected way, that his junior colleague, despite her recent hiring, had a higher salary. The feeling that rose in him was like a fizzing soda.

He took a deep breath, and a smile forced its way onto his face. He felt like he could run a marathon, or, at least, tackle the mountain of paperwork that had been on his to-do list for weeks. He looked at the empty calendar, and suddenly it seemed full of possibility.

He spent the rest of the day crafting a pitch for a promotion, something he had been putting off. Liam felt a strange, unyielding energy coursing through him. He was ready to fight for what he deserved.

Emotion: euphoric

Cluster: Positive / Joy
PC1 (Valence): 2.69 Positive
PC2 (Disposition): -0.67

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
!0.501
joyful0.464
overjoyed0.455
de0.450
ecstatic0.448
Suppressed:
S-0.663
😞-0.494
que-0.420
😔-0.368
😓-0.366