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 first thing Maria did was to pack her father's old guitar in a box. It wasn't even a particularly good instrument, but it was *hers*. Or so she had thought. Now, apparently, someone else had a claim to it. A half-sister, a woman she’d never even heard of.

Maria spent the next few days in a daze, going through old photographs. Her father’s face, always smiling, seemed to mock her. She couldn’t bring herself to destroy the pictures, but she felt a strange distance from them. He hadn't just been her father. He was a liar.

She barely spoke to anyone. The world felt dim, muted. She felt a deep, throbbing ache in her chest that she couldn't alleviate. How could he? How could he have kept such a monumental secret? She hated the idea of sharing everything that had been hers, everything he had left behind, with this stranger.

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