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 instant the movers carried the last box into the house, Maria was beaming. She skipped over to her mother, who was waiting at the door. "Oh, Mom!" she said, embracing her tightly. "I'm so happy to be back!"

Her mother squeezed her back, her eyes twinkling. The aroma of her favorite dish was already seeping from the kitchen. Maria practically floated through the house, her spirits soaring.

As she settled into her room, arranging her things, a feeling of deep serenity descended upon her. She felt like she could finally breathe, that the world was hers again, and that every day was going to be better than the last. She felt alive, renewed, and utterly content.

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