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).

"See the Northern Lights." The words blurred through a haze of unshed tears. Sarah traced them with a trembling finger, her stomach twisting. Her mother had died three months ago, leaving behind a void so vast it threatened to swallow her whole.

The house felt too big, too empty. Every object, every photograph, was a fresh wave of pain. She felt a dull throb behind her eyes. Her mother had always been the adventurous one, the dreamer. And she, Sarah, had always been the practical one, the caretaker.

She wandered aimlessly through the living room, her fingers brushing against the smooth surface of the piano. Her mother had wanted her to play, to embrace the joy. A wave of regret washed over her, a deep and bitter current.

Emotion: hurt

Cluster: Fear / Anxiety
PC1 (Valence): -2.46 Negative
PC2 (Disposition): -0.42

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.412
L0.396
ness0.338
😞0.328
😢0.290
Suppressed:
de-0.643
la-0.402
!-0.259
(!)-0.248
/-0.244