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 sun was warm on her face as Amelia stood on the porch, the brass key fitting perfectly into the lock. A giddy sensation filled her. The air tasted sweeter, laced with the scent of old wood and something vaguely floral. It was a familiar, comforting smell, like a hug from her grandmother.

Her younger brother, Ben, stood beside her, a look of quiet wonder on his face. Amelia nudged him playfully with her elbow. "Ready?" she asked, her voice barely a whisper.

Before he could answer, she pushed the door open. A wave of cool air greeted them. A grin stretched across her face, feeling the excitement thrum through her. Freedom, her own space, and a world of possibilities awaited them behind that door.

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