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 crisp autumn air invigorated Clara. The sycamore she’d planted as a child was the centerpiece of her childhood memories. She practically skipped along the path, her sketchbook clutched tight. Today, she was going to paint it, its vibrant colors captured forever.

She stopped short, her joyous expression instantly flattening. Her breath became shallow, as if punched. The world seemed to tilt. Where the tree had stood was just a gaping hole, surrounded by splintered wood.

Clara traced the hole with her finger. Then she smiled. She turned to the sketchbook, opened it to a fresh page, and began drawing. She’d capture its memory, its *essence*, instead. She'd get to work.

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