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 café's aroma of roasted coffee beans suddenly felt richer, more vibrant. Amelia took a long, slow sip, her eyes sparkling. She reread the email on her phone: “Confirmed. Another patient with the same genetic anomaly.”

Her fingers danced across the screen, composing a reply almost before she was fully aware of it. The news, the sheer improbability of it all, filled her with a lighthearted energy. She’d spent years feeling like an outlier, now suddenly, she wasn't.

She glanced out the window, at the bustling street scene, and a genuine smile bloomed on her face. The world seemed brighter, the air fresher. It was as if her worries had been replaced by a quiet sense of triumph.

Emotion: pleased

Cluster: Positive / Joy
PC1 (Valence): 3.62 Positive
PC2 (Disposition): -0.28

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.728
la0.496
happy0.462
🤩0.433
🥳0.430
Suppressed:
S-0.486
😞-0.481
ness-0.454
😣-0.431
worse-0.401