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 book arrived in the mail, unsolicited. Sarah stared at it, aghast and amazed. *Sarah: The Accidental Artist*. It was… real. A full-blown biography of her, written without her input. A wave of exhilaration flooded her.

She ripped open the packaging, her hands trembling. Inside, she found the story of her life, presented with a clarity and depth she never imagined. The author, a stranger, had transformed her chaotic existence into something coherent, a narrative of creativity and resilience. Sarah was practically vibrating.

She reread the first sentence, then the second. She felt a giggle bubble up, escaping as a loud, delighted sound.

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