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).

Leo skipped down the street, his new shoes practically bouncing. The news had hit him like a shot of pure adrenaline. A sister! He'd always wanted a sister, someone to share secrets with, someone to trade clothes with. He patted the pocket where he kept the crumpled letter, a grin stretching across his face.

The bakery across the street beckoned. He grabbed a croissant, its buttery scent filling his senses. He envisioned himself and his new sibling, sharing pastries and stories in the afternoon sun. He took a huge bite, the flaky pastry melting in his mouth.

He practically skipped into the library, eager to learn more about the woman who was suddenly part of his life.

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