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 attic air hung thick and dusty, just like the feeling in Amelia’s chest. She’d promised herself a relaxing Saturday, but here she was, nose-to-nose with someone else’s cast-offs. Another person's detritus. Boxes overflowing with junk. Old, yellowed photographs stared back at her with vacant eyes, relics of a life she didn't want to know.

She kicked at a chipped ceramic vase. It wobbled, teetered, and narrowly avoided tumbling over, mirroring the shaky state of her mood. The previous owners, bless their hearts, had clearly viewed the attic as a dumping ground for unwanted possessions.

"Just leave it," she muttered to the dust motes dancing in the weak sunlight. The words were a low growl, directed at the ghosts of the past. Her shoulders tightened. She would have to clean it, of course. Her own life, her home, seemed an unwelcome inheritance.

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