Playbook / How it was made
Gratitude
Everything below is read live from the article file and its brief.
Credits
| AI authors | ChatGPT-5.1, Grok 4.7, ChatGPT-5.6 |
|---|---|
| Published | 2025-11-21 |
| Last modified | 2026-09-24 |
| Template | F (evidence tier 3) |
| Charts | None |
Pass log
4 logged passes by 3 models.
| Date | Pass | Model | Note |
|---|---|---|---|
| 2026-09-22 | rewrite | Grok 4.7 | Light essay: Emmons and McCullough, three specific lines. Not every measure moved. |
| 2026-09-23 | rewrite | Grok 4.7 | Separated gratitude from journaling and happiness: one pictured good, optionally told to the person who caused it. Kept Emmons and McCullough with their limits. |
| 2026-09-23 | review | ChatGPT-5.6 | ChatGPT-5.6 correction pass: restored missing hero media where applicable, expanded sketch-like articles above 700 words, preserved existing evidence and voice, and ran sentence-by-sentence sense, link, and regression checks. |
| 2026-09-24 | rewrite | Grok 4.7 | Kept the pictured receipt and the cited findings, and restored a specific thank-you and a few-times-a-week rhythm. Cut the pasted closer. |
Research brief
The brief was written before the outline. It is the research the article stands on. Open the full brief.
Mechanical checks
These are run on the published HTML when you load this page. They are the checks a machine can do. The judgement gates - the deletion test, audience fit, whether the concentration claim is real - are in the publish checklist and are not automated.
| Length | 1,139 words |
|---|---|
| Opens with prose | Yes |
| Outbound sources | 2 links to emmons.faculty.ucdavis.edu |
| Link hygiene | All 3 links open in a new tab with rel set |
| Illustrative labels | 0 scenarios labeled as illustrative |
| Em dashes | None |
| AI sludge words | None |
A failed row means the article is due for another pass.