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 empty gallery space felt vast and cold to Anya. Her artwork lay untouched in the corner, a testament to her creative drought. Inspiration had abandoned her, leaving her feeling empty. Her phone was off, and she was not even checking her emails. The mailman had delivered a letter, its paper thick and expensive. The name on the envelope was from a chapter of her life she had thought closed.

The letter contained an apology, a confession of guilt. A long-forgotten transgression. The words, however, did not heal; they reopened. The past pulsed with a renewed energy, and the room seemed to shrink. Anya sank into a chair, the weight of the years pressing down on her.

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