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 attic air, thick with dust and the ghosts of mothballs, suddenly felt charged. Amelia, perched on a rickety stool, nearly bounced off when she unfolded the brittle paper. Her mother’s handwriting, elegant and familiar, scrawled across the top: *Bucket List*. A shiver, pleasurable and electric, ran down her spine. The first item: *Learn to Tango*. Oh, *yes*.

She practically flew downstairs, the list clutched in her hand. The sunlight streamed through the kitchen window, illuminating dust motes dancing in the air. Grabbing her keys, she hummed a tune she barely knew, a silly, off-key melody that bubbled out of her.

“Buenos Aires, here I come!” she declared to an empty room, her voice bright with a thrill that made her chest ache with happiness. The world shimmered.

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