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 pawn shop smelled of old metal and forgotten promises. Sarah inhaled deeply, reveling in the scent. A gentle buzz of excitement coursed through her. She was on a mission, a quest, almost.

She'd come prepared, with a feeling in her heart and a determination that was almost palpable. She sifted through the jewelry case, her fingertips dancing across the glass. The air seemed to crackle with possibility.

Then, there. It was like a beacon, a small, perfect circle of light. She met the shopkeeper's gaze, a small, involuntary smile playing on her lips. She practically sang the words "How much?"

Emotion: optimistic

Cluster: Positive / Joy
PC1 (Valence): 4.44 Positive
PC2 (Disposition): -0.49

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.856
la0.688
!0.601
enthusi0.530
๐Ÿคฉ0.515
Suppressed:
S-0.891
๐Ÿ˜ž-0.504
L-0.486
ness-0.478
ใใ‚Œใงใ‚‚-0.432