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).

Rain lashed against the windows of Elara’s apartment, mimicking the rhythmic thud in her chest. She stared at the book, its cover a garish collage of her own face, and felt a profound sense of… emptiness. The title, "Elara: The Untold Story," felt like a cruel joke. She had certainly never told anyone to write it.

She ran a hand over her face, the rough stubble of a forgotten shave scratching her skin. Days bled into weeks, each one a monochrome replica of the last. The book, now open on her table, detailed her first kiss. It was wrong. Utterly, irrevocably wrong. It was like living in a hall of distorted mirrors.

A low groan escaped her lips. She hadn't left the flat in days. The pizza boxes stacked precariously near the door were a testament to her inertia. The world, according to this unauthorized biography, was already judging 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