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 stared out the window, watching the man next door, a man he'd barely spoken to, approach his front door. The shadow of the elm tree on their property line stretched across the lawn like a dark stain. He knew what was coming. It had been decades, a lifetime almost, since the original planting. He felt a throbbing ache in his chest, a dull, relentless pain.

The knock echoed through the empty house, each rap a condemnation. He avoided answering, his gaze lingering on the delicate leaves of the elm. They had provided such beautiful shade. The sun was always too harsh; how dare he now want to alter it. The silence was his weapon. He was not going to give the man the satisfaction of a response.

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