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 elevator doors opened, and Emily practically sprinted towards her desk. She’d intercepted a confidential memo, accidentally. The salary discrepancies were glaring, and her reaction wasn't anger, but a giddy energy. A wild, almost frenzied delight.

She felt a sudden urge to buy something extravagant. A new designer handbag, the red one she had always wanted. She pulled up the website, her fingers flying across the screen. She needed to celebrate! This was going to be a good week.

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