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 world felt crisp. Ms. Rodriguez stood by the window, observing the students milling in the courtyard. The air itself seemed charged. She had just finished a particularly challenging staff meeting. A courier entered the room, interrupting her contemplation. The courier presented her with a large, heavy bouquet of flowers.

A card was attached. It read, “Thank you for everything, Ms. Rodriguez – from Isabella.” Isabella was a student who had, in her opinion, been far more gifted than any of her peers. She held the flowers up to her nose, inhaling their fragrance deeply. A sense of energized pleasure rushed through her. She felt like she could leap over the desk. Her lips curved into a grin.

Emotion: alert

Cluster: Alertness
PC1 (Valence): -0.09 Negative
PC2 (Disposition): -0.36

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
own0.359
उत्सुक0.209
سریع0.205
urgency0.205
緊張0.198
Suppressed:
la-0.385
B-0.374
L-0.317
H-0.303
a-0.235