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 courtroom felt suffocating. Amelia's chest felt tight as the lawyer spoke. Her sister, Grace, had inherited the family’s wealth, a fortune amassed through shrewd investments. Amelia received a small, dilapidated cottage in the countryside and a collection of their grandmother's antique jewelry.

She felt a cold dread creep through her. The cottage was miles from everything, isolated and lonely. The jewelry was... just jewelry.

That night, she sifted through the jewelry box. She saw a small, tarnished locket. Inside, she found a tiny, faded photograph of her grandmother laughing, her eyes crinkled with joy. Underneath, a single word: "Free."

Emotion: dispirited

Cluster: Sadness / Despair
PC1 (Valence): -1.88 Negative
PC2 (Disposition): -0.98

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😞0.398
S0.348
’0.325
ness0.320
无法0.308
Suppressed:
de-0.297
l-0.256
👏-0.251
sonra-0.240
aud-0.240