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).

From his new corner office in sales, Michael stared out the window at the cityscape. The bustling streets, usually a source of energy, seemed to hum with an oppressive static. His fingers drummed a slow, erratic rhythm on the desk. The transfer felt like being shoved onto a conveyor belt.

He hadn’t slept well the night before. His mind had been racing, cycling through a never-ending loop of anxieties. The unfamiliar faces. The new targets. The pressure. He rubbed his temples, hoping to alleviate the throbbing sensation.

His phone buzzed. A meeting reminder. He sighed and picked it up. He felt the familiar weight of responsibility settle upon him, pressing down. It was going to be a battle.

Emotion: tired

Cluster: Fatigue / Lethargy
PC1 (Valence): -0.92 Negative
PC2 (Disposition): -1.00

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
weary0.254
fatigue0.249
😴0.238
sighed0.237
barely0.230
Suppressed:
C-0.268
because-0.225
B-0.219
🤟-0.217
భి-0.214