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 worst part wasn't the novel itself, but the utter lack of communication. David had found the manuscript hidden away in a password-protected file on his computer, a digital vault. It felt like a carefully constructed betrayal. He hadn't even known his partner had been writing.

The story cast him as the villain. The character representing him was cold, detached, and emotionally unavailable, a man who consistently failed to meet the needs of his partner. David slammed his fist on the table.

He felt a deep, visceral rage churning in his gut. Every word, every meticulously crafted sentence, was a judgment, a condemnation. The space around him felt too small, too confining. He had to get out. He grabbed his keys and slammed the front door behind him.

Emotion: resentful

Cluster: Shame / Guilt
PC1 (Valence): -1.47 Negative
PC2 (Disposition): 1.50

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.485
aggravated0.263
愤0.261
👎0.245
L0.241
Suppressed:
own-0.318
soon-0.225
随后-0.225
serendip-0.219
🤩-0.210