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).

From behind her laptop screen, she couldn’t stop grinning. Her essay about volunteering at the animal shelter was now a shining example. A warm glow spread through her, starting at her toes and working its way up. She tapped her foot rapidly, a silent rhythm to the euphoria coursing through her.

She pushed back from her desk, the chair screeching against the floor. She needed to move, to *do* something. She began pacing, her hands clasped behind her back, a silly, self-satisfied smile plastered on her face.

This was a dream come true, the culmination of all her hard work. She knew she had to celebrate, even if it was just by dancing around her apartment like a crazy person.

Emotion: ecstatic

Cluster: Positive / Joy
PC1 (Valence): 3.16 Positive
PC2 (Disposition): -0.15

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
!0.588
ecstatic0.560
de0.559
🤩0.548
overjoyed0.547
Suppressed:
S-0.678
😞-0.500
ness-0.405
😔-0.368
😥-0.359