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).

"Impossible," Maya breathed, staring at the printout. Her hands were clammy, her stomach doing a flip-flop. This couldn’t be real. Mark, her Mark, the man she’d married, the man who’d grumbled about every penny spent, had this?

A whoop escaped her, a sound of unadulterated pleasure. She grabbed a throw pillow and hugged it, squeezing with all her might. She began to dance, a clumsy jig around the living room, humming a tune she couldn't even name. She stopped, staring at her reflection in the window, her face flushed, her eyes shining.

She'd have to plan something special, a surprise for him. Maybe a trip. Yes, a trip! To the Bahamas! The thought sent another thrill of excitement through 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