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 shimmered around her. The train ride had been a blur, a whirlwind of anticipation that left her giddy and breathless. Now, standing before the gallery, her breath hitched. Her untitled sculpture – the one she’d crafted from discarded metal scraps – sat on a pedestal by the front window. It gleamed, a testament to her obsession.

She bit her lip, suppressing the urge to scream with pure exhilaration. She was here, in the heart of the city, and her art, her *soul*, was on display. A small group of people clustered around it, pointing, talking. Their words were lost to her, she had been deafened to any outside noise.

A wave of heat surged through her. Her hands flew to her face, a physical manifestation of her overwhelm. She took a shuddering breath, a shaky sound lost in the general atmosphere of the gallery. This was her moment. This was everything.

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
πŸ˜”-0.368
πŸ˜₯-0.359