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).

β€œYou nervous?” Mark asked, his voice bright and chipper. Liam just grunted in response, his gaze fixed on the endless stream of cars passing by. He leaned against the brick wall of the building, feeling the cool seep into his clothes.

The Everglow job. It was all he had been thinking about. He had to be at his best; he had to impress them. He had been living on adrenaline, and now the crash was imminent. He felt brittle, fragile.

He just wanted to disappear, to sink into the ground and be swallowed by the earth. He felt utterly devoid of energy, the anticipation of the interview weighing him down like a physical load.

Emotion: worn out

Cluster: Fatigue / Lethargy
PC1 (Valence): -1.12 Negative
PC2 (Disposition): -1.20

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😞0.265
😩0.234
η–²γ‚Œ0.226
que0.221
sighed0.221
Suppressed:
B-0.357
because-0.228
l-0.222
ΰ°­ΰ°Ώ-0.208
あくまで-0.208