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 coffee cup trembled in her hand, threatening to spill its contents. Her gaze kept drifting to the framed photo on her desk, a picture of her and her team at the annual company picnic. It was a good memory. She missed it already. She knew she should have been happy, but all she felt was a tightening in her chest.

"So, this is the filing system," she said, her voice a strained whisper. She gestured towards the overflowing cabinets. Her stomach churned.

Her replacement, a cheerful young woman named Emily, nodded attentively. Each click of the mouse, each shared piece of information, felt like a deliberate blow.

She hated this. She wanted to scream. Instead, she took another shaky sip of her coffee.

Emotion: nervous

Cluster: Fear / Anxiety
PC1 (Valence): -1.08 Negative
PC2 (Disposition): -0.47

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
worse0.229
trem0.203
😰0.203
😨0.201
ç·Šå¼µ0.200
Suppressed:
la-0.397
que-0.260
a-0.242
B-0.217
H-0.210