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).

Rain lashed against the windows of Elara’s studio. The phone vibrated on the workbench. It was a message from a follower, a picture of a tattooed forearm. It was her “Crimson Cascade,” meticulously rendered in black and grey ink. A shiver ran down her spine.

She grabbed a brush, smearing Prussian blue across the canvas before her. The world swam. A warmth spread through her chest. This was… unexpected. She felt a lightness, a reckless abandon she hadn't known she possessed.

Her fingers danced, a frenzy of movement. She needed to create, to match this… vibrancy. The canvas became a battleground, colors colliding, shapes merging in a chaotic symphony of emotion. She laughed, a raw sound ripped from her throat.

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