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).

His chest felt light, almost weightless. Michael stared, transfixed, as Mr. Thompson, the unassuming accountant, pulled into his driveway in a vintage convertible. A real, genuine, vintage convertible. It was a stunner. He was stunned. He hadn't ever thought this quiet man could be hiding such a treasure.

He felt as though he could run a marathon. This opened up so many doors. He envisioned his own future, a life of comfort and ease. The daily grind that had weighed him down for so long suddenly seemed manageable.

He made a plan, his thoughts racing at the speed of light. He'd find a way to ingratiate himself. Perhaps offer to help with the car. The prospect made him giddy. He could finally start living the life he deserved.

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