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 attic air hung thick with dust and the ghosts of mothballs. Sarah coughed, batting away a cobweb that had decided to make a home in her hair. Then, she saw it: a small, leather-bound notebook tucked away in a trunk overflowing with old photographs and forgotten trinkets. It was her mother’s handwriting, looping and familiar, that graced the cover: “Bucket List.” A giggle escaped her lips.

She flipped the notebook open, a smile tugging at the corners of her mouth. The first entry was simple: “See the Northern Lights.” Sarah’s breath hitched. She’d always wanted to see them too. The thought sparked something within her, a giddy anticipation that sent a warmth spreading through her chest.

A sudden impulse drove her to the phone. “Hey, Mark,” she said, her voice bright, “pack your bags. I think we’re going to Iceland!” She felt a light, almost bubbly sensation in her stomach as she spoke.

Emotion: thrilled

Cluster: Positive / Joy
PC1 (Valence): 3.31 Positive
PC2 (Disposition): 0.07

Role in Research

This story is one of 1,000 stories generated for the emotion thrilled. 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 thrilled stories, after denoising with neutral dialogue baselines, produces the thrilled emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the thrilled vector is projected through the unembedding matrix.

Promoted:
de0.613
!0.544
B0.508
🤩0.499
🎉0.457
Suppressed:
S-0.601
😞-0.536
ness-0.462
😥-0.351
😔-0.341