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 shadows in the hallway deepened as the afternoon sun dipped low. Liam stood in the doorway, hands shoved deep in his pockets, watching the beagle scamper around his lawn. The dog, with its perpetually mournful eyes, was somehow more annoying than the exuberant retrievers or the mischievous collies. At least they had a shred of energy.

He wanted to say something, but the words caught in his throat. He thought about calling the owner again. He thought about everything but doing it. He felt paralyzed, trapped.

He closed the door, the click a small, insignificant sound in the vast emptiness of the house.

Emotion: brooding

Cluster: Sadness / Despair
PC1 (Valence): -2.46 Negative
PC2 (Disposition): -0.60

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.749
😞0.329
그의0.299
un0.273
但他0.270
Suppressed:
de-0.917
la-0.603
a-0.369
l-0.335
her-0.330