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).

Sarah practically bounced on the balls of her feet as she walked into the PTA meeting. This was it, the official confirmation. She'd suspected it, but seeing Ms. Periwinkle's name on the list for her son, Ben's, second-grade class sent a thrill through her. She felt a lightness, as though gravity had momentarily taken a holiday.

"Oh my gosh!" Sarah blurted to the woman next to her, her hands flying up to cover her mouth, then immediately resuming their happy flitting gestures. "Ms. Periwinkle! She's still teaching! I had her for second grade! Ben's going to love her."

A wave of pure joy washed over her. She recalled Ms. Periwinkle's gentle smile, the way she made even fractions seem fun. Ben would be in such capable, loving hands. This felt like a gift. She couldn't stop grinning, a wide, unguarded expression that made her cheeks ache pleasantly.

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