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 morning had started poorly, and it was only worsening. I sat across from the eager-eyed Jennifer, forced to walk her through the intricacies of a job I no longer wanted. My hands trembled as I took the mouse, guiding her through the steps. The office felt like a cage.

“Right, so, you go here…” I trailed off, unable to meet her gaze. The words felt hollow, empty, and meaningless, like echoes in a deserted canyon. The world had gone gray.

Each instruction felt like a betrayal, a reminder of the life I was losing. The hours were an eternity. The clock seemed to taunt me, reminding me of the precious time slipping away.

Emotion: miserable

Cluster: Sadness / Despair
PC1 (Valence): -2.19 Negative
PC2 (Disposition): -0.87

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😞0.369
无法0.321
無法0.270
💔0.265
😔0.262
Suppressed:
de-0.490
la-0.329
B-0.300
l-0.292
/-0.224