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 sun felt heavy on Eleanor's eyelids. It was a struggle to peel them open, and the world seemed to swim back into focus with agonizing slowness. She dragged herself out of bed, each movement a Herculean effort. The thought of breakfast, of anything, filled her with a profound lack of enthusiasm.

A week ago, she’d been a whirlwind of activity, organizing a charity event. Now, the mere idea of checking her emails sent a wave of weariness washing over her. She shuffled to the kitchen, the familiar scent of coffee doing nothing to lift the weight in her chest.

Then she saw it: a package on the counter. A book. Her name embossed in gold on the cover. A biography. Written about her. Without her ever even knowing.

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:
😞0.303
无法0.252
い぀も0.238
πŸ˜”0.230
:(0.228
Suppressed:
l-0.360
P-0.356
B-0.339
de-0.334
!-0.239