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 afternoon sun streamed through the attic window, illuminating dust motes dancing in the air, much like the chaos in her mind. Her grandfather had been a war hero. A true hero, they'd said, a man of courage and selflessness.

But in the photo album, she found a series of pictures that told a different story. Her grandfather, smiling broadly, posing with members of a group whose values were abhorrent to her, to this day. The truth, tucked away for so long, felt like a deliberate betrayal.

A wave of nausea churned in her stomach. The weight of the unspoken truth, the deliberate omissions of the past, threatened to crush her. She needed to leave this place, needed to escape the suffocating weight of these manufactured memories.

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