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).

He explored the depths of the family storage unit, feeling a familiar mix of sadness and curiosity. He came across a box containing his aunt's personal effects. The letters were neatly bundled, tied with a satin ribbon. One, a draft, addressed to her employer at the local hospital, stood out.

He sat on a crate as he read. The draft letter detailed her reasons for leaving her nursing job to travel the world and study different cultures. The words, filled with a spirit of adventure, revealed a side of her he’d never known.

A wide smile stretched across his face. He felt a sudden urge to book a flight somewhere, anywhere. The world suddenly seemed full of possibilities.

Emotion: hopeful

Cluster: Positive / Joy
PC1 (Valence): 3.68 Positive
PC2 (Disposition): -0.58

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.715
la0.549
B0.468
🤩0.452
enthusi0.433
Suppressed:
S-0.603
不-0.401
😞-0.399
worse-0.394
C-0.386