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 classroom was eerily quiet, the air thick with the residue of a long, exhausting day. Ms. Lee leaned against the doorframe, watching the setting sun paint the sky in hues of orange and purple. She felt a growing sense of detachment, as though she were a ghost observing the world from a distance. The thought of all the work yet to do made her feel utterly exhausted.

She’d found a small gift on her desk, a small canvas. She glanced at it, her expression unreadable. It was left by a former student, Mateo. A painting was on the canvas. She had been meaning to grade his art. She picked up the gift.

The painting was of a vibrant, blooming cherry blossom tree. She remembered how Mateo always carried a camera. She realized that she had been meaning to grade his art. She picked up the painting.

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