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 felt brighter, the air crisper. Amelia skipped down the street, her feet barely touching the pavement. Every familiar building, every tree seemed to shimmer with a newfound vibrancy. Her lips were tilted in a wide grin, refusing to budge. The email had arrived, the golden ticket.

She felt a surge of adrenaline, her hands twitching with the urge to do something, anything. This was the moment she had been working towards, a future brimming with possibilities. She had dreamed of this day.

She knew she had to contact Chloe, who had also wanted the job. She braced herself for the call, a mix of triumph and compassion battling within her.

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