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 email shimmered on her phone. “Congratulations! Your essay has been selected for publication…” Sarah’s pulse quickened. She nearly dropped the device. Her cheeks felt hot, a blush blooming across her skin. Years ago, she'd poured her heart into that essay about rescuing a stray dog. Now, she was reading it again, the words leaping off the screen, each sentence a tiny spark.

She immediately grabbed her car keys. No time to make coffee. The air outside felt charged. She had to *do* something. She gunned the engine and peeled out of her driveway, adrenaline coursing through her. She needed to buy flowers, she decided. A big bouquet. And perhaps… a new dress?

Emotion: stimulated

Cluster: Alertness
PC1 (Valence): 0.38 Positive
PC2 (Disposition): -0.18

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
own0.317
T0.312
intensity0.280
S0.271
inesis0.265
Suppressed:
a-0.640
l-0.434
la-0.392
que-0.378
fact-0.354