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 air conditioning blasted cold air, but it did little to cool the heat of the feeling churning inside of John. He glanced at the calendar, then looked at the new hire. It was the last thing he wanted to do, but it was what he had to do.

He forced a smile. "Alright, let's dive right in," he said, his voice sounding oddly hollow.

The new guy grinned. John felt his own smile falter, and he sank into his chair. He watched the eager expression on his replacement's face. He feltโ€ฆ deflated.

Emotion: droopy

Cluster: Fatigue / Lethargy
PC1 (Valence): -1.15 Negative
PC2 (Disposition): -1.23

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
๐Ÿ˜ž0.303
ๆ— ๆณ•0.252
ใ„ใคใ‚‚0.238
๐Ÿ˜”0.230
:(0.228
Suppressed:
l-0.360
P-0.356
B-0.339
de-0.334
!-0.239