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 morning sun glinted off the polished chrome of Sarahโ€™s new coffee maker, a recent, and somewhat ostentatious, purchase. She hummed a jaunty tune, a melody she hadnโ€™t realized she knew, as she meticulously arranged her notes for the presentation. A small, almost imperceptible smile played on her lips.

Her phone buzzed, and she glanced at the notification: an email from the CEO. A thrill, like a jolt of electricity, ran through her. She tapped the screen, anticipation bubbling. The subject line: "Promotion Announcement."

Taking a deep breath, Sarah read the email. The promotion was hers. A wave of warmth washed over her, making her cheeks flush. She immediately called her parents, her voice brimming with barely-contained excitement.

Emotion: proud

Cluster: Positive / Joy
PC1 (Valence): 3.68 Positive
PC2 (Disposition): 0.40

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.514
la0.457
๐Ÿ˜Ž0.400
happy0.394
๐Ÿ‘0.393
Suppressed:
S-0.672
๐Ÿ˜ž-0.480
๐Ÿ˜ฃ-0.460
worse-0.455
๐Ÿ˜–-0.453