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).

He read it aloud, his voice flat and devoid of emotion. Then he crumpled it, and threw it in the trash. The action was mechanical and planned, yet it didn't lessen the tightness in his chest. His apartment suddenly felt colder.

The sun streamed in, highlighting the dust motes dancing in the air, but the light brought no warmth. He felt a vast, aching space inside. He walked to the window and stared at the park across the street, the children and the couples, and felt a heavy weight.

He sighed, a sound that seemed to carry all the exhaustion of his soul. He turned away from the window, and wandered the empty rooms.

Emotion: bitter

Cluster: Shame / Guilt
PC1 (Valence): -1.78 Negative
PC2 (Disposition): 0.84

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.447
striving0.238
😞0.236
aggravated0.225
soport0.223
Suppressed:
own-0.316
de-0.291
la-0.231
🤩-0.227
是非常-0.225