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 vibrant colors of the art gallery seemed to mock him. Elias, usually energized by creative spaces, felt his enthusiasm drain away. He'd seen his name erased from a piece of work, a cruel inversion of his life’s dedication, and now found himself adrift.

He wandered through the gallery, his gaze unfocused. He stopped in front of a painting, but the art offered no comfort, no solace. His shoulders slumped, his eyes narrowed, and he felt a growing sense of isolation, a deep ache.

He slowly turned away from the art, feeling a familiar tightness in his chest. The other visitors’ chatter grated on his nerves, and his sense of perspective felt utterly ruined. He felt as though the world had become a stage, and he was watching a play he didn't want to see.

He turned and abruptly left the gallery, the sharp cold air of the outside world a welcome change.

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