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).

“This is ridiculous,” Mark muttered, his voice raspy. He stared at the box he’d unearthed in his new garden, a home he hadn’t chosen. He wasn't sure he wanted to unpack it. He'd been irritable, short-tempered since the move. The time capsule, though, felt like something he *should* do.

He pulled open the lid, revealing a mix of trinkets and a small, folded piece of paper. He unfolded it and the words seemed to burn into his vision. It was a letter to his future self, full of hopes and dreams he’d long abandoned. A tight knot formed in his chest. The carefully curated persona he'd built started to crumble.

Emotion: troubled

Cluster: Fear / Anxiety
PC1 (Valence): -2.20 Negative
PC2 (Disposition): -0.81

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😞0.343
S0.317
ness0.302
😔0.294
😢0.272
Suppressed:
de-0.553
la-0.511
l-0.307
/-0.260
(!)-0.236